Merge branch 'master' into ci-write-less-ccache

.github/workflows/close-issue.yml

@@ -17,7 +17,7 @@ jobs:
     steps:
       - uses: actions/stale@v5
         with:
-          exempt-issue-labels: "refactor,help wanted,good first issue,research,bug"
+          exempt-issue-labels: "refactor,help wanted,good first issue,research,bug,roadmap"
           days-before-issue-stale: 30
           days-before-issue-close: 14
           stale-issue-label: "stale"

AUTHORS

@@ -1,4 +1,4 @@
-# date: Thu Nov 28 20:46:15 EET 2024
+# date: Tue Feb  4 13:04:05 EET 2025
 # this file is auto-generated by scripts/gen-authors.sh
 
 0cc4m <picard12@live.de>
@@ -20,6 +20,8 @@ Adithya Balaji <adithya.b94@gmail.com>
 AdithyanI <adithyan.i4internet@gmail.com>
 Adrian <smith.adriane@gmail.com>
 Adrian Hesketh <a-h@users.noreply.github.com>
+Adrien Gallouët <adrien@gallouet.fr>
+Adrien Gallouët <angt@huggingface.co>
 Ahmad Tameem <113388789+Tameem-10xE@users.noreply.github.com>
 Ahmet Zeer <ahmed.zeer@std.yildiz.edu.tr>
 AidanBeltonS <87009434+AidanBeltonS@users.noreply.github.com>
@@ -55,6 +57,7 @@ Ananta Bastola <anantarajbastola@gmail.com>
 Anas Ahouzi <112881240+aahouzi@users.noreply.github.com>
 András Salamon <ott2@users.noreply.github.com>
 Andreas (Andi) Kunar <andreask@msn.com>
+Andreas Kieslinger <47689530+aendk@users.noreply.github.com>
 Andrei <abetlen@gmail.com>
 Andrew Canis <andrew.canis@gmail.com>
 Andrew Downing <andrew2085@gmail.com>
@@ -91,13 +94,17 @@ Ben Siraphob <bensiraphob@gmail.com>
 Ben Williams <ben@719ben.com>
 Benjamin Findley <39356821+Kartoffelsaft@users.noreply.github.com>
 Benjamin Lecaillon <84293038+blecaillon@users.noreply.github.com>
+Benson Wong <mostlygeek@gmail.com>
 Bernat Vadell <hounter.caza@gmail.com>
+Bernhard M. Wiedemann <githubbmwprimary@lsmod.de>
 Bert Wagner <github@bertwagner.com>
+Billel Mokeddem <billel.mokeddem.ml@gmail.com>
 Bingan <70050083+binganao@users.noreply.github.com>
 Bjarke Viksøe <164612031+bviksoe@users.noreply.github.com>
 Bodo Graumann <mail@bodograumann.de>
 Bono Lv <lvscar@users.noreply.github.com>
 Borislav Stanimirov <b.stanimirov@abv.bg>
+Borislav Stanimirov <b@ibob.bg>
 Branden Butler <bwtbutler@hotmail.com>
 Brandon Squizzato <35474886+bsquizz@users.noreply.github.com>
 Brian <mofosyne@gmail.com>
@@ -117,6 +124,7 @@ Casey Primozic <casey@cprimozic.net>
 Casey Primozic <me@ameo.link>
 CausalLM <148736309+CausalLM@users.noreply.github.com>
 Cebtenzzre <cebtenzzre@gmail.com>
+CentricStorm <CentricStorm@users.noreply.github.com>
 Chad Brewbaker <crb002@gmail.com>
 Changyeon Kim <cyzero.kim@samsung.com>
 Chao Jiang <jc19chaoj@zoho.com>
@@ -131,12 +139,15 @@ Chris Kuehl <ckuehl@ckuehl.me>
 Christian Demsar <christian@github.email.demsar.us>
 Christian Demsar <crasm@git.vczf.us>
 Christian Falch <875252+chrfalch@users.noreply.github.com>
+Christian Kastner <ckk@kvr.at>
 Christian Kögler <ck3d@gmx.de>
 Christian Köhnenkamp <cvk5@me.com>
 Christian Zhou-Zheng <59622928+christianazinn@users.noreply.github.com>
+Christopher Nielsen <62156882+mascguy@users.noreply.github.com>
 Clark Saben <76020733+csaben@users.noreply.github.com>
 Clint Herron <hanclinto@gmail.com>
 Conrad Kramer <conrad@conradkramer.com>
+Corentin REGAL <corentin.regal@gmail.com>
 CrispStrobe <154636388+CrispStrobe@users.noreply.github.com>
 Csaba Kecskemeti <csaba.kecskemeti@gmail.com>
 Cuong Trinh Manh <nguoithichkhampha@gmail.com>
@@ -176,6 +187,7 @@ Dibakar Gope <dibakar.gope@arm.com>
 Didzis Gosko <didzis@users.noreply.github.com>
 Diego Devesa <slarengh@gmail.com>
 Diogo Teles Sant'Anna <diogoteles@google.com>
+Djip007 <3705339+Djip007@users.noreply.github.com>
 Djip007 <djip.perois@free.fr>
 Don Mahurin <dmahurin@users.noreply.github.com>
 DooWoong Lee (David) <manics99@naver.com>
@@ -193,6 +205,7 @@ Edward Taylor <edeetee@gmail.com>
 Elaine <elaine.zosa@gmail.com>
 Elbios <141279586+Elbios@users.noreply.github.com>
 Elton Kola <eltonkola@gmail.com>
+Emreerdog <34742675+Emreerdog@users.noreply.github.com>
 Engininja2 <139037756+Engininja2@users.noreply.github.com>
 Equim <sayaka@ekyu.moe>
 Eric Curtin <ecurtin@redhat.com>
@@ -233,6 +246,7 @@ Fred Douglas <43351173+fredlas@users.noreply.github.com>
 Frederik Vogel <Schaltfehler@users.noreply.github.com>
 Gabe Goodhart <gabe.l.hart@gmail.com>
 Gabe Goodhart <ghart@us.ibm.com>
+Gaetan Bisson <gaetan@fenua.org>
 GainLee <perfecter.gen@gmail.com>
 Galunid <karolek1231456@gmail.com>
 Gary Linscott <glinscott@gmail.com>
@@ -249,6 +263,7 @@ Guillaume "Vermeille" Sanchez <Guillaume.V.Sanchez@gmail.com>
 Guillaume Wenzek <gwenzek@users.noreply.github.com>
 Guoliang Hua <32868157+nbcsm@users.noreply.github.com>
 Guoteng <32697156+SolenoidWGT@users.noreply.github.com>
+Guspan Tanadi <36249910+guspan-tanadi@users.noreply.github.com>
 Gustavo Rocha Dias <91472747+gustrd@users.noreply.github.com>
 Haggai Nuchi <h.nuchi@gmail.com>
 Halalaluyafail3 <55773281+Halalaluyafail3@users.noreply.github.com>
@@ -259,11 +274,13 @@ Haoxiang Fei <tonyfettes@tonyfettes.com>
 Harald Fernengel <harald.fernengel@here.com>
 Hatsune Miku <129688334+at8u@users.noreply.github.com>
 HatsuneMikuUwU33 <173229399+HatsuneMikuUwU33@users.noreply.github.com>
+Haus1 <haus.xda@gmail.com>
 Henk Poley <HenkPoley@gmail.com>
 Henri Vasserman <henv@hot.ee>
 Henrik Forstén <henrik.forsten@gmail.com>
 Herman Semenov <GermanAizek@yandex.ru>
 Hesen Peng <hesen.peng@gmail.com>
+HimariO <dsfhe49854@gmail.com>
 Hoang Nguyen <hugo53@users.noreply.github.com>
 Hong Bo PENG <penghb@cn.ibm.com>
 Hongyu Ouyang <96765450+casavaca@users.noreply.github.com>
@@ -280,6 +297,7 @@ Icecream95 <the.real.icecream95@gmail.com>
 Ido S <ido.pluto@gmail.com>
 IgnacioFDM <ignaciofdm@gmail.com>
 Igor Okulist <okigan@gmail.com>
+Ihar Hrachyshka <ihrachys@redhat.com>
 Ikko Eltociear Ashimine <eltociear@gmail.com>
 Ilya Kurdyukov <59548320+ilyakurdyukov@users.noreply.github.com>
 Ionoclast Laboratories <brigham@ionoclast.com>
@@ -289,12 +307,14 @@ Ivan <nekotekina@gmail.com>
 Ivan Filipov <159561759+vanaka11@users.noreply.github.com>
 Ivan Komarov <Ivan.Komarov@dfyz.info>
 Ivan Stepanov <ivanstepanovftw@gmail.com>
+JFLFY2255 <JFLFY2255@163.com>
 JH23X <165871467+JH23X@users.noreply.github.com>
 Jack Mousseau <jack@software.inc>
 Jack Mousseau <jmousseau@users.noreply.github.com>
 JackJollimore <130917767+JackJollimore@users.noreply.github.com>
 Jaeden Amero <jaeden@patater.com>
 Jaemin Son <woalsdnd@gmail.com>
+Jafar Uruç <jafar.uruc@gmail.com>
 Jag Chadha <jagtesh@gmail.com>
 Jakub N <jakubniemczyk97@gmail.com>
 James A Capozzoli <157492257+jac-jim@users.noreply.github.com>
@@ -315,6 +335,7 @@ Jeffrey Morgan <jmorganca@gmail.com>
 Jeffrey Quesnelle <emozilla@nousresearch.com>
 Jeroen Mostert <jeroen.mostert@cm.com>
 Jesse Jojo Johnson <williamsaintgeorge@gmail.com>
+Jett Janiak <jettjaniak@gmail.com>
 Jeximo <jeximo@gmail.com>
 Jhen-Jie Hong <iainst0409@gmail.com>
 Jiahao Li <liplus17@163.com>
@@ -343,6 +364,7 @@ Josh Ramer <josh.ramer@icloud.com>
 Joyce <joycebrum@google.com>
 Juan Calderon-Perez <835733+gaby@users.noreply.github.com>
 Judd <foldl@users.noreply.github.com>
+Juk Armstrong <69222624+jukofyork@users.noreply.github.com>
 Julius Arkenberg <arki05@users.noreply.github.com>
 Jun Hee Yoo <contact.jhyoo@gmail.com>
 Jun Jie <71215065+junnjiee16@users.noreply.github.com>
@@ -357,6 +379,7 @@ Justine Tunney <jtunney@mozilla.com>
 Juuso Alasuutari <juuso.alasuutari@gmail.com>
 KASR <karim.asrih@gmail.com>
 Kamil Tomšík <info@tomsik.cz>
+Karol Kontny <82021046+kkontny@users.noreply.github.com>
 Karsten Weiss <knweiss@gmail.com>
 Karthick <j.karthic2004@gmail.com>
 Karthik Kumar Viswanathan <195178+guilt@users.noreply.github.com>
@@ -376,6 +399,7 @@ Kolen Cheung <ickc@users.noreply.github.com>
 Konstantin Herud <konstantin.herud@denkbares.com>
 Konstantin Zhuravlyov <konstantin.zhuravlyov@amd.com>
 Kunshang Ji <kunshang.ji@intel.com>
+Kyle Bruene <KyleBruene@users.noreply.github.com>
 Kyle Liang <liangmanlai@gmail.com>
 Kyle Mistele <kyle@mistele.com>
 Kylin <56434533+KyL0N@users.noreply.github.com>
@@ -394,6 +418,7 @@ Liu Jia <jia3.liu@intel.com>
 LoganDark <github@logandark.mozmail.com>
 Loïc Carrère <loic.carrere@gmail.com>
 LostRuins <39025047+LostRuins@users.noreply.github.com>
+LostRuins Concedo <39025047+LostRuins@users.noreply.github.com>
 Luciano <lucianostrika44@gmail.com>
 Luo Tian <lt@basecity.com>
 Lyle Dean <dean@lyle.dev>
@@ -423,6 +448,7 @@ MasterYi1024 <39848311+MasterYi1024@users.noreply.github.com>
 Mateusz Charytoniuk <mateusz.charytoniuk@protonmail.com>
 Matheus C. França <matheus-catarino@hotmail.com>
 Matheus Gabriel Alves Silva <matheusgasource@gmail.com>
+Mathieu Baudier <mbaudier@argeo.org>
 Mathieu Geli <mathieu.geli@gmail.com>
 Mathieu Nayrolles <MathieuNls@users.noreply.github.com>
 Mathijs Henquet <mathijs.henquet@gmail.com>
@@ -444,6 +470,7 @@ Meng, Hengyu <hengyu.meng@intel.com>
 Mengqing Cao <cmq0113@163.com>
 Merrick Christensen <merrick.christensen@gmail.com>
 Michael Coppola <m18coppola@gmail.com>
+Michael Engel <mengel@redhat.com>
 Michael Francis <edude03@gmail.com>
 Michael Hueschen <m@mhueschen.dev>
 Michael Kesper <mkesper@schokokeks.org>
@@ -452,7 +479,9 @@ Michael Podvitskiy <podvitskiymichael@gmail.com>
 Michael Potter <NanoTekGuy@Gmail.com>
 Michael de Gans <michael.john.degans@gmail.com>
 Michaël de Vries <vriesdemichael@gmail.com>
+Michał Moskal <michal@moskal.me>
 Michał Tuszyński <srgtuszy@gmail.com>
+Michelle Tan <41475767+MichelleTanPY@users.noreply.github.com>
 Mihai <mihai.chirculescu@yahoo.com>
 Mike <ytianhui2004@gmail.com>
 Mikko Juola <mikjuo@gmail.com>
@@ -477,6 +506,7 @@ Neo Zhang <14088817+arthw@users.noreply.github.com>
 Neo Zhang <zhang.jianyu@outlook.com>
 Neo Zhang Jianyu <jianyu.zhang@intel.com>
 Neuman Vong <neuman.vong@gmail.com>
+NeverLucky <92274250+nvrxq@users.noreply.github.com>
 Nexes the Old <124105151+Nexesenex@users.noreply.github.com>
 Nexesenex <124105151+Nexesenex@users.noreply.github.com>
 Niall Coates <1349685+Niall-@users.noreply.github.com>
@@ -484,11 +514,15 @@ Nicholai Tukanov <nicholaitukanov@gmail.com>
 Nico Bosshard <nico@bosshome.ch>
 Nicolai Weitkemper <kontakt@nicolaiweitkemper.de>
 Nicolás Pérez <nicolas_perez@brown.edu>
+Nicolò Scipione <nicolo.scipione@codeplay.com>
 Nigel Bosch <pnigelb@gmail.com>
+Nikita Sarychev <42014488+sARY77@users.noreply.github.com>
 Niklas Korz <niklas@niklaskorz.de>
 NikolaiLyssogor <59844691+NikolaiLyssogor@users.noreply.github.com>
+Nikolaos Pothitos <pothitos@di.uoa.gr>
 Nikolas <127742645+nneubacher@users.noreply.github.com>
 Nindaleth <Nindaleth@users.noreply.github.com>
+Nuno <rare-magma@posteo.eu>
 OSecret <135510162+OLSecret@users.noreply.github.com>
 Oleksandr Nikitin <oleksandr@tvori.info>
 Oleksii Maryshchenko <oleksii.maryshchenko@gmail.com>
@@ -504,6 +538,7 @@ Pavel Zloi <github.com@drteam.rocks>
 Pavol Rusnak <pavol@rusnak.io>
 Paweł Wodnicki <151604+32bitmicro@users.noreply.github.com>
 Pedro Cuenca <pedro@huggingface.co>
+Peter <peter277@users.noreply.github.com>
 Peter Sugihara <peter@campsh.com>
 Phil H <5756783+phiharri@users.noreply.github.com>
 Philip Taron <philip.taron@gmail.com>
@@ -529,9 +564,12 @@ Rand Xie <randxiexyy29@gmail.com>
 Randall Fitzgerald <randall@dasaku.net>
 Random Fly <renfei8@live.cn>
 Reinforce-II <fate@eastal.com>
+Rémy Oudompheng <oudomphe@phare.normalesup.org>
 Ren Xuancheng <jklj077@users.noreply.github.com>
 Rene Leonhardt <65483435+reneleonhardt@users.noreply.github.com>
+Reza Kakhki <rezakakhki.de@gmail.com>
 RhinoDevel <RhinoDevel@users.noreply.github.com>
+Riccardo Orlando <Riccorl@users.noreply.github.com>
 Riceball LEE <snowyu.lee@gmail.com>
 Rich Dougherty <rich@rd.nz>
 Richard Kiss <him@richardkiss.com>
@@ -544,6 +582,8 @@ Riley Stewart <ristew@users.noreply.github.com>
 Rinne <AsakusaRinne@gmail.com>
 Rinne <liu_yaohui1998@126.com>
 Robert Brisita <986796+rbrisita@users.noreply.github.com>
+Robert Collins <roberto.tomas.cuentas@gmail.com>
+Robert Ormandi <52251610+ormandi@users.noreply.github.com>
 Robert Sung-wook Shin <edp1096@users.noreply.github.com>
 Robey Holderith <robey@flaminglunchbox.net>
 Robyn <robyngraf@users.noreply.github.com>
@@ -559,7 +599,9 @@ Roni <sulpher@gmx.net>
 Ronny Brendel <ronnybrendel@gmail.com>
 Ronsor <ronsor@ronsor.pw>
 Rowan Hart <rowanbhart@gmail.com>
+Ruan <47767371+ruanych@users.noreply.github.com>
 Ruchira Hasaranga <ruchira66@gmail.com>
+Rudi Servo <rudiservo@gmail.com>
 Ruixin Huang <18860020911@163.com>
 Rune <43761327+Rune-AI@users.noreply.github.com>
 RunningLeon <maningsheng@sensetime.com>
@@ -623,12 +665,14 @@ Steven Roussey <sroussey@gmail.com>
 Steward Garcia <57494570+FSSRepo@users.noreply.github.com>
 StrangeBytesDev <141275258+StrangeBytesDev@users.noreply.github.com>
 Suaj Carrot <72162667+SuajCarrot@users.noreply.github.com>
+Sukriti Sharma <Ssukriti@users.noreply.github.com>
 SuperUserNameMan <yoann@terminajones.com>
 Sutou Kouhei <kou@cozmixng.org>
 Tai Duc Nguyen <taiducnguyen.drexel@gmail.com>
 Taikono-Himazin <kazu@po.harenet.ne.jp>
 Tameem <113388789+AhmadTameem@users.noreply.github.com>
 Tamotsu Takahashi <ttakah+github@gmail.com>
+Tei Home <taiteitonghome@proton.me>
 Thái Hoàng Tâm <75922889+RoyalHeart@users.noreply.github.com>
 Thatcher Chamberlin <j.thatcher.c@gmail.com>
 Theia Vogel <theia@vgel.me>
@@ -640,6 +684,7 @@ Tim Miller <drasticactions@users.noreply.github.com>
 Tim Wang <overocean@gmail.com>
 Timmy Knight <r2d2fish@gmail.com>
 Timothy Cronin <40186632+4imothy@users.noreply.github.com>
+Ting Lou <louting@189.cn>
 Ting Lou <ting.lou@gmail.com>
 Ting Sun <suntcrick@gmail.com>
 Tobias Lütke <tobi@shopify.com>
@@ -661,6 +706,7 @@ Uzo Nweke <uzoechi@gmail.com>
 Vaibhav Srivastav <vaibhavs10@gmail.com>
 Val Kharitonov <mail@kharvd.com>
 Valentin Konovalov <valle.ketsujin@gmail.com>
+Valentin Mamedov <45292985+Inf1delis@users.noreply.github.com>
 Valentyn Bezshapkin <61702053+valentynbez@users.noreply.github.com>
 Vali Malinoiu <0x4139@gmail.com>
 Victor Nogueira <felladrin@gmail.com>
@@ -673,13 +719,17 @@ Vladimir Malyutin <first-leon@yandex.ru>
 Vladimir Zorin <vladimir@deviant.guru>
 VoidIsVoid <343750470@qq.com>
 Volodymyr Vitvitskyi <72226+signalpillar@users.noreply.github.com>
+Wang Qin <37098874+wangqin0@users.noreply.github.com>
+Wang Ran (汪然) <wangr@smail.nju.edu.cn>
 WangHaoranRobin <56047610+WangHaoranRobin@users.noreply.github.com>
 Weird Constructor <weirdconstructor@gmail.com>
 Welby Seely <welbyseely@gmail.com>
 Wentai Zhang <rchardx@gmail.com>
 WillCorticesAI <150854901+WillCorticesAI@users.noreply.github.com>
 William Tambellini <william.tambellini@gmail.com>
+William Tambellini <wtambellini@sdl.com>
 Willy Tarreau <w@1wt.eu>
+Woof Dog <197125663+woof-dog@users.noreply.github.com>
 Wouter <9594229+DifferentialityDevelopment@users.noreply.github.com>
 Wu Jian Ping <wujjpp@hotmail.com>
 Wu Jian Ping <wujp@greatld.com>
@@ -692,6 +742,7 @@ Xie Yanbo <xieyanbo@gmail.com>
 Xingchen Song(宋星辰) <xingchensong1996@163.com>
 Xinpeng Dou <81913537+Dou-Git@users.noreply.github.com>
 Xuan Son Nguyen <thichthat@gmail.com>
+Xuan-Son Nguyen <thichthat@gmail.com>
 Yaiko <elyaiko@hotmail.com>
 Yann Follet <131855179+YannFollet@users.noreply.github.com>
 Yaroslav <yaroslav.yashin@me.com>
@@ -702,7 +753,9 @@ Yoshi Suhara <y.suhara@gmail.com>
 Yoshi Suhara <ysuhara@nvidia.com>
 Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
 Yueh-Po Peng <94939112+y10ab1@users.noreply.github.com>
+Yüg <eugeniosegalaweb@gmail.com>
 Yui <dev@sleepyyui.com>
+Yun Dou <dixyes@gmail.com>
 Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
 Yusuf Kağan Hanoğlu <hanoglu@yahoo.com>
 Yuval Peled <31162840+Yuval-Peled@users.noreply.github.com>
@@ -714,18 +767,23 @@ Zhang Peiyuan <a1286225768@gmail.com>
 Zheng.Deng <32841220+dengzheng-cloud@users.noreply.github.com>
 Zhenwei Jin <109658203+kylo5aby@users.noreply.github.com>
 Zhiyuan Li <lizhiyuan@uniartisan.com>
+Zhiyuan Li <uniartisan2017@gmail.com>
 ZhouYuChen <zhouyuchen@naver.com>
 Ziad Ben Hadj-Alouane <zied.benhadjalouane@gmail.com>
 Ziang Wu <97337387+ZiangWu-77@users.noreply.github.com>
 Zsapi <martin1.zsapka@gmail.com>
 a-n-n-a-l-e-e <150648636+a-n-n-a-l-e-e@users.noreply.github.com>
+a3sh <38979186+A3shTnT@users.noreply.github.com>
 adel boussaken <netdur@gmail.com>
 afrideva <95653597+afrideva@users.noreply.github.com>
+ag2s20150909 <19373730+ag2s20150909@users.noreply.github.com>
 agray3 <agray3@users.noreply.github.com>
 akawrykow <142945436+akawrykow@users.noreply.github.com>
+alek3y <44779186+alek3y@users.noreply.github.com>
 alexpinel <93524949+alexpinel@users.noreply.github.com>
 alonfaraj <alonfaraj@gmail.com>
 alwqx <kenan3015@gmail.com>
+amd-dwang <dong.wang@amd.com>
 amd-lalithnc <lalithnc@amd.com>
 amritahs-ibm <amritahs@linux.vnet.ibm.com>
 andrijdavid <david@geek.mg>
@@ -737,6 +795,7 @@ arch-btw <57669023+arch-btw@users.noreply.github.com>
 arcrank <arcrank@gmail.com>
 ardfork <134447697+ardfork@users.noreply.github.com>
 arlo-phoenix <140345165+arlo-phoenix@users.noreply.github.com>
+aryantandon01 <80969509+aryantandon01@users.noreply.github.com>
 at8u <129688334+at8u@users.noreply.github.com>
 automaticcat <daogiatuank54@gmail.com>
 awatuna <23447591+awatuna@users.noreply.github.com>
@@ -751,12 +810,14 @@ bryanSwk <93190252+bryanSwk@users.noreply.github.com>
 bsilvereagle <bsilvereagle@users.noreply.github.com>
 bssrdf <merlintiger@hotmail.com>
 byte-6174 <88070277+byte-6174@users.noreply.github.com>
+cduk <19917266+cduk@users.noreply.github.com>
 cebtenzzre <cebtenzzre@gmail.com>
 chaihahaha <chai836275709@gmail.com>
 chiranko <96988916+chiranko@users.noreply.github.com>
 clibdev <52199778+clibdev@users.noreply.github.com>
 clyang <clyang@clyang.net>
 cocktailpeanut <121128867+cocktailpeanut@users.noreply.github.com>
+codezjx <code.zjx@gmail.com>
 coezbek <c.oezbek@gmail.com>
 comex <comexk@gmail.com>
 compilade <113953597+compilade@users.noreply.github.com>
@@ -780,14 +841,17 @@ drbh <david.richard.holtz@gmail.com>
 ds5t5 <145942675+ds5t5@users.noreply.github.com>
 dylan <canardleteer@users.noreply.github.com>
 eastriver <lee@eastriver.dev>
+ebraminio <ebrahim@gnu.org>
 ebraminio <ebraminio@gmail.com>
 eiery <19350831+eiery@users.noreply.github.com>
 eric8607242 <e0928021388@gmail.com>
 fairydreaming <166155368+fairydreaming@users.noreply.github.com>
 fengerhu1 <2748250768@qq.com>
+fj-y-saito <85871716+fj-y-saito@users.noreply.github.com>
 fraxy-v <65565042+fraxy-v@users.noreply.github.com>
 github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 gliptic <gliptic@users.noreply.github.com>
+gn64 <yukikaze.jp@gmail.com>
 goerch <jhr.walter@t-online.de>
 grahameth <96447521+grahameth@users.noreply.github.com>
 gtygo <gtydoit@gmail.com>
@@ -812,10 +876,12 @@ icppWorld <124377669+icppWorld@users.noreply.github.com>
 igarnier <igarnier@protonmail.com>
 intelmatt <61025942+intelmatt@users.noreply.github.com>
 iohub <rickyang.pro@gmail.com>
+issixx <46835150+issixx@users.noreply.github.com>
 jacobi petrucciani <8117202+jpetrucciani@users.noreply.github.com>
 jaime-m-p <167997752+jaime-m-p@users.noreply.github.com>
 jameswu2014 <545426914@qq.com>
 jdomke <28772296+jdomke@users.noreply.github.com>
+jiahao su <damow890@gmail.com>
 jiez <373447296@qq.com>
 jneem <joeneeman@gmail.com>
 joecryptotoo <80373433+joecryptotoo@users.noreply.github.com>
@@ -828,6 +894,7 @@ junchao-loongson <68935141+junchao-loongson@users.noreply.github.com>
 jwj7140 <32943891+jwj7140@users.noreply.github.com>
 k.h.lai <adrian.k.h.lai@outlook.com>
 kaizau <kaizau@users.noreply.github.com>
+kallewoof <kalle.alm@gmail.com>
 kalomaze <66376113+kalomaze@users.noreply.github.com>
 kang <tpdns9032100@gmail.com>
 katsu560 <118887472+katsu560@users.noreply.github.com>
@@ -835,6 +902,7 @@ kchro3 <62481661+kchro3@users.noreply.github.com>
 khimaros <me@khimaros.com>
 kiltyj <kiltyj@gmail.com>
 klosax <131523366+klosax@users.noreply.github.com>
+krystiancha <krystian@krystianch.com>
 kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
 kunnis <kunnis@users.noreply.github.com>
 kuronekosaiko <EvanChanJ@163.com>
@@ -847,6 +915,8 @@ ldwang <ftgreat@163.com>
 le.chang <cljs118@126.com>
 leejet <leejet714@gmail.com>
 leo-pony <nengjunma@outlook.com>
+lexasub <lexakopp2212@gmail.com>
+lhez <quic_lih@quicinc.com>
 limitedAtonement <limitedAtonement@users.noreply.github.com>
 liuwei-git <14815172+liuwei-git@users.noreply.github.com>
 lon <114724657+longregen@users.noreply.github.com>
@@ -855,10 +925,13 @@ ltoniazzi <61414566+ltoniazzi@users.noreply.github.com>
 luoyu-intel <yu.luo@intel.com>
 m3ndax <adrian.goessl@outlook.com>
 maddes8cht <55592906+maddes8cht@users.noreply.github.com>
+mahorozte <41834471+mahorozte@users.noreply.github.com>
 makomk <makosoft@googlemail.com>
 manikbhandari <mbbhandarimanik2@gmail.com>
 maor-ps <154728172+maor-ps@users.noreply.github.com>
+mashdragon <122402293+mashdragon@users.noreply.github.com>
 matiaslin <45382001+matiaslin@users.noreply.github.com>
+matt23654 <matthew.webber@protonmail.com>
 matteo <matteogeniaccio@yahoo.it>
 mdrokz <mohammadmunshi@gmail.com>
 mgroeber9110 <45620825+mgroeber9110@users.noreply.github.com>
@@ -868,6 +941,7 @@ mmyjona <jonathan.gonse@gmail.com>
 momonga <115213907+mmnga@users.noreply.github.com>
 momonga <146910567+mmngays@users.noreply.github.com>
 moritzbrantner <31051084+moritzbrantner@users.noreply.github.com>
+musoles <135031143+musoles@users.noreply.github.com>
 mzcu <milos.cubrilo@gmail.com>
 nanahi <130121847+na-na-hi@users.noreply.github.com>
 ngc92 <7938269+ngc92@users.noreply.github.com>
@@ -885,6 +959,7 @@ oobabooga <112222186+oobabooga@users.noreply.github.com>
 opparco <parco.opaai@gmail.com>
 ostix360 <55257054+ostix360@users.noreply.github.com>
 pculliton <phillipculliton@gmail.com>
+peidaqi <peidaqi@gmail.com>
 pengxin99 <pengxin.yuan@intel.com>
 perserk <perserk@gmail.com>
 piDack <104877312+piDack@users.noreply.github.com>
@@ -892,10 +967,12 @@ pmysl <piotr.myslinski@outlook.com>
 postmasters <namnguyen@google.com>
 pudepiedj <pudepiedj@gmail.com>
 qingfengfenga <41416092+qingfengfenga@users.noreply.github.com>
+qingy1337 <qxli2@students.everettcc.edu>
 qouoq <qouoq@fastmail.com>
 qunash <anzoria@gmail.com>
 rabidcopy <rabidcopy@yahoo.com>
 rankaiyx <rankaiyx@rankaiyx.com>
+redbeard <bharrington@alticon.net>
 rhjdvsgsgks <26178113+rhjdvsgsgks@users.noreply.github.com>
 rhuddleston <ryan.huddleston@percona.com>
 rimoliga <53384203+rimoliga@users.noreply.github.com>
@@ -912,6 +989,7 @@ sjxx <63994076+ylsdamxssjxxdd@users.noreply.github.com>
 slaren <2141330+slaren@users.noreply.github.com>
 slaren <slarengh@gmail.com>
 snadampal <87143774+snadampal@users.noreply.github.com>
+someone13574 <81528246+someone13574@users.noreply.github.com>
 standby24x7 <standby24x7@gmail.com>
 staviq <staviq@gmail.com>
 stduhpf <stephduh@live.fr>
@@ -931,6 +1009,7 @@ uint256_t <konndennsa@gmail.com>
 uint256_t <maekawatoshiki1017@gmail.com>
 unbounded <haakon@likedan.net>
 uvos <devnull@uvos.xyz>
+uvos <philipp@uvos.xyz>
 valiray <133289098+valiray@users.noreply.github.com>
 vb <vaibhavs10@gmail.com>
 vik <vikhyatk@gmail.com>
@@ -951,6 +1030,7 @@ xaedes <xaedes@googlemail.com>
 xctan <axunlei@gmail.com>
 xloem <0xloem@gmail.com>
 yangli2 <yangli2@gmail.com>
+ymcki <84055651+ymcki@users.noreply.github.com>
 yuiseki <yuiseki@gmail.com>
 yuri@FreeBSD <yurivict@users.noreply.github.com>
 zakkor <edward.partenie@gmail.com>
@@ -963,4 +1043,5 @@ zrm <trustiosity.zrm@gmail.com>
 杨朱 · Kiki <baofa.fan@daocloud.io>
 源文雨 <41315874+fumiama@users.noreply.github.com>
 蕭澧邦 <45505768+shou692199@users.noreply.github.com>
+谢乃闻 <sienaiwun@users.noreply.github.com>
 Нияз Гарифзянов <112617865+garrnizon@users.noreply.github.com>

README.md

@@ -136,6 +136,7 @@ Instructions for adding support for new models: [HOWTO-add-model.md](docs/develo
 - Rust (more features): [edgenai/llama_cpp-rs](https://github.com/edgenai/llama_cpp-rs)
 - Rust (nicer API): [mdrokz/rust-llama.cpp](https://github.com/mdrokz/rust-llama.cpp)
 - Rust (more direct bindings): [utilityai/llama-cpp-rs](https://github.com/utilityai/llama-cpp-rs)
+- Rust (automated build from crates.io): [ShelbyJenkins/llm_client](https://github.com/ShelbyJenkins/llm_client)
 - C#/.NET: [SciSharp/LLamaSharp](https://github.com/SciSharp/LLamaSharp)
 - C#/VB.NET (more features - community license): [LM-Kit.NET](https://docs.lm-kit.com/lm-kit-net/index.html)
 - Scala 3: [donderom/llm4s](https://github.com/donderom/llm4s)

common/chat.cpp

@@ -365,7 +365,7 @@ static common_chat_params common_chat_params_init_command_r7b(const common_chat_
     return data;
 }
 static common_chat_msg common_chat_parse_command_r7b(const std::string & input) {
-    static std::regex response_regex("<\\|START_RESPONSE\\|>(.*?)<\\|END_RESPONSE\\|>");
+    static std::regex response_regex("<\\|START_RESPONSE\\|>([\\s\\S\\n\\r]*?)<\\|END_RESPONSE\\|>");
     static std::regex thought_action_regex("<\\|START_THINKING\\|>([\\s\\S\\n\\r]*?)<\\|END_THINKING\\|><\\|START_ACTION\\|>([\\s\\S\\n\\r]*?)<\\|END_ACTION\\|>");
     std::smatch match;
 

common/common.cpp

@@ -1869,11 +1869,19 @@ std::string common_chat_format_example(const common_chat_template & tmpl, bool u
     return common_chat_apply_template(tmpl, msgs, true, use_jinja);
 }
 
+#define CHATML_TEMPLATE_SRC \
+    "{%- for message in messages -%}\n" \
+    "  {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' -}}\n" \
+    "{%- endfor -%}\n" \
+    "{%- if add_generation_prompt -%}\n" \
+    "  {{- '<|im_start|>assistant\n' -}}\n" \
+    "{%- endif -%}"
+
 common_chat_templates common_chat_templates_from_model(const struct llama_model * model, const std::string & chat_template_override)
 {
-    auto vocab = llama_model_get_vocab(model);
+    std::string default_template_src;
-    std::string default_template_src = chat_template_override;
+    std::string template_tool_use_src;
-    std::string template_tool_use_src = chat_template_override;
+
     bool has_explicit_template = !chat_template_override.empty();
     if (chat_template_override.empty()) {
         auto str = llama_model_chat_template(model, /* name */ nullptr);
@@ -1886,21 +1894,21 @@ common_chat_templates common_chat_templates_from_model(const struct llama_model
             template_tool_use_src = str;
             has_explicit_template = true;
         }
+    } else {
+        default_template_src = chat_template_override;
     }
     if (default_template_src.empty() || default_template_src == "chatml") {
         if (!template_tool_use_src.empty()) {
             default_template_src = template_tool_use_src;
         } else {
-            default_template_src = R"(
+            default_template_src = CHATML_TEMPLATE_SRC;
-                {%- for message in messages -%}
-                    {{- "<|im_start|>" + message.role + "\n" + message.content + "<|im_end|>\n" -}}
-                {%- endfor -%}
-                {%- if add_generation_prompt -%}
-                    {{- "<|im_start|>assistant\n" -}}
-                {%- endif -%}
-            )";
         }
     }
+    std::string token_bos;
+    std::string token_eos;
+    // TODO: update logic that adds BOS and EOS tokens to the tokenized prompt, in favour of the template.
+#if 0
+    auto vocab = llama_model_get_vocab(model);
     const auto get_token = [&](llama_token token, const char * name, const char * jinja_variable_name) {
         if (token == LLAMA_TOKEN_NULL) {
             if (default_template_src.find(jinja_variable_name) != std::string::npos
@@ -1912,15 +1920,25 @@ common_chat_templates common_chat_templates_from_model(const struct llama_model
             return common_token_to_piece(vocab, token, true);
         }
     };
-    auto token_bos = get_token(llama_vocab_bos(vocab), "BOS", "bos_token");
+    token_bos = get_token(llama_vocab_bos(vocab), "BOS", "bos_token");
-    auto token_eos = get_token(llama_vocab_eos(vocab), "EOS", "eos_token");
+    token_eos = get_token(llama_vocab_eos(vocab), "EOS", "eos_token");
-    return {
+#endif
-        has_explicit_template,
+    try {
-        std::make_unique<minja::chat_template>(default_template_src, token_bos, token_eos),
+        return {
-        template_tool_use_src.empty()
+            has_explicit_template,
-            ? nullptr
+            std::make_unique<minja::chat_template>(default_template_src, token_bos, token_eos),
-            : std::make_unique<minja::chat_template>(template_tool_use_src, token_bos, token_eos)
+            template_tool_use_src.empty()
-    };
+                ? nullptr
+                : std::make_unique<minja::chat_template>(template_tool_use_src, token_bos, token_eos),
+        };
+    } catch (const std::exception & e) {
+        LOG_ERR("%s: failed to parse chat template: %s\n", __func__, e.what());
+        return {
+            has_explicit_template,
+            std::make_unique<minja::chat_template>(CHATML_TEMPLATE_SRC, token_bos, token_eos),
+            nullptr,
+        };
+    }
 }
 
 //

examples/batched.swift/Sources/main.swift

@@ -31,6 +31,11 @@ defer {
     llama_model_free(model)
 }
 
+guard let vocab = llama_model_get_vocab(model) else {
+    print("Failed to get vocab")
+    exit(1)
+}
+
 var tokens = tokenize(text: prompt, add_bos: true)
 
 let n_kv_req = UInt32(tokens.count) + UInt32((n_len - Int(tokens.count)) * n_parallel)
@@ -41,7 +46,7 @@ context_params.n_batch = UInt32(max(n_len, n_parallel))
 context_params.n_threads = 8
 context_params.n_threads_batch = 8
 
-let context = llama_new_context_with_model(model, context_params)
+let context = llama_init_from_model(model, context_params)
 guard context != nil else {
     print("Failed to initialize context")
     exit(1)
@@ -141,7 +146,7 @@ while n_cur <= n_len {
         let new_token_id = llama_sampler_sample(smpl, context, i_batch[i])
 
         // is it an end of stream? -> mark the stream as finished
-        if llama_vocab_is_eog(model, new_token_id) || n_cur == n_len {
+        if llama_vocab_is_eog(vocab, new_token_id) || n_cur == n_len {
             i_batch[i] = -1
             // print("")
             if n_parallel > 1 {
@@ -207,7 +212,7 @@ private func tokenize(text: String, add_bos: Bool) -> [llama_token] {
     let utf8Count = text.utf8.count
     let n_tokens = utf8Count + (add_bos ? 1 : 0)
     let tokens = UnsafeMutablePointer<llama_token>.allocate(capacity: n_tokens)
-    let tokenCount = llama_tokenize(model, text, Int32(utf8Count), tokens, Int32(n_tokens), add_bos, /*special tokens*/ false)
+    let tokenCount = llama_tokenize(vocab, text, Int32(utf8Count), tokens, Int32(n_tokens), add_bos, /*special tokens*/ false)
     var swiftTokens: [llama_token] = []
     for i in 0 ..< tokenCount {
         swiftTokens.append(tokens[Int(i)])
@@ -218,12 +223,12 @@ private func tokenize(text: String, add_bos: Bool) -> [llama_token] {
 
 private func token_to_piece(token: llama_token, buffer: inout [CChar]) -> String? {
     var result = [CChar](repeating: 0, count: 8)
-    let nTokens = llama_token_to_piece(model, token, &result, Int32(result.count), 0, false)
+    let nTokens = llama_token_to_piece(vocab, token, &result, Int32(result.count), 0, false)
     if nTokens < 0 {
         let actualTokensCount = -Int(nTokens)
         result = .init(repeating: 0, count: actualTokensCount)
         let check = llama_token_to_piece(
-            model,
+            vocab,
             token,
             &result,
             Int32(result.count),

examples/llama.swiftui/llama.cpp.swift/LibLlama.swift

@@ -24,6 +24,7 @@ func llama_batch_add(_ batch: inout llama_batch, _ id: llama_token, _ pos: llama
 actor LlamaContext {
     private var model: OpaquePointer
     private var context: OpaquePointer
+    private var vocab: OpaquePointer
     private var sampling: UnsafeMutablePointer<llama_sampler>
     private var batch: llama_batch
     private var tokens_list: [llama_token]
@@ -47,6 +48,7 @@ actor LlamaContext {
         self.sampling = llama_sampler_chain_init(sparams)
         llama_sampler_chain_add(self.sampling, llama_sampler_init_temp(0.4))
         llama_sampler_chain_add(self.sampling, llama_sampler_init_dist(1234))
+        vocab = llama_model_get_vocab(model)
     }
 
     deinit {
@@ -79,7 +81,7 @@ actor LlamaContext {
         ctx_params.n_threads       = Int32(n_threads)
         ctx_params.n_threads_batch = Int32(n_threads)
 
-        let context = llama_new_context_with_model(model, ctx_params)
+        let context = llama_init_from_model(model, ctx_params)
         guard let context else {
             print("Could not load context!")
             throw LlamaError.couldNotInitializeContext
@@ -151,7 +153,7 @@ actor LlamaContext {
 
         new_token_id = llama_sampler_sample(sampling, context, batch.n_tokens - 1)
 
-        if llama_vocab_is_eog(model, new_token_id) || n_cur == n_len {
+        if llama_vocab_is_eog(vocab, new_token_id) || n_cur == n_len {
             print("\n")
             is_done = true
             let new_token_str = String(cString: temporary_invalid_cchars + [0])
@@ -297,7 +299,7 @@ actor LlamaContext {
         let utf8Count = text.utf8.count
         let n_tokens = utf8Count + (add_bos ? 1 : 0) + 1
         let tokens = UnsafeMutablePointer<llama_token>.allocate(capacity: n_tokens)
-        let tokenCount = llama_tokenize(model, text, Int32(utf8Count), tokens, Int32(n_tokens), add_bos, false)
+        let tokenCount = llama_tokenize(vocab, text, Int32(utf8Count), tokens, Int32(n_tokens), add_bos, false)
 
         var swiftTokens: [llama_token] = []
         for i in 0..<tokenCount {
@@ -316,7 +318,7 @@ actor LlamaContext {
         defer {
             result.deallocate()
         }
-        let nTokens = llama_token_to_piece(model, token, result, 8, 0, false)
+        let nTokens = llama_token_to_piece(vocab, token, result, 8, 0, false)
 
         if nTokens < 0 {
             let newResult = UnsafeMutablePointer<Int8>.allocate(capacity: Int(-nTokens))
@@ -324,7 +326,7 @@ actor LlamaContext {
             defer {
                 newResult.deallocate()
             }
-            let nNewTokens = llama_token_to_piece(model, token, newResult, -nTokens, 0, false)
+            let nNewTokens = llama_token_to_piece(vocab, token, newResult, -nTokens, 0, false)
             let bufferPointer = UnsafeBufferPointer(start: newResult, count: Int(nNewTokens))
             return Array(bufferPointer)
         } else {

examples/server/tests/unit/test_chat_completion.py

@@ -13,9 +13,12 @@ def create_server():
 @pytest.mark.parametrize(
     "model,system_prompt,user_prompt,max_tokens,re_content,n_prompt,n_predicted,finish_reason,jinja,chat_template",
     [
+        (None, "Book", "Hey", 8, "But she couldn't", 69, 8, "length", False, None),
+        (None, "Book", "Hey", 8, "But she couldn't", 69, 8, "length", True, None),
         (None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", False, None),
-        (None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", True, None),
+        (None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", True,  None),
-        (None, "Book", "What is the best book", 8, "^ blue", 23, 8, "length", True, "This is not a chat template, it is"),
+        (None, "Book", "What is the best book", 8, "(Suddenly)+|\\{ \" Sarax.", 77, 8, "length", True, 'chatml'),
+        (None, "Book", "What is the best book", 8, "^ blue",                    23, 8, "length", True, "This is not a chat template, it is"),
         ("codellama70b", "You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 64, "length", False, None),
         ("codellama70b", "You are a coding assistant.", "Write the fibonacci function in c++.", 128, "(Aside|she|felter|alonger)+", 104, 64, "length", True, None),
     ]

examples/server/tests/unit/test_tool_call.py

@@ -67,8 +67,8 @@ WEATHER_TOOL = {
 
 
 def do_test_completion_with_required_tool_tiny(template_name: str, tool: dict, argument_key: str | None):
-    n_predict = 512
     global server
+    n_predict = 512
     # server = ServerPreset.stories15m_moe()
     server.jinja = True
     server.n_predict = n_predict
@@ -139,29 +139,49 @@ def test_completion_with_required_tool_tiny_slow(template_name: str, tool: dict,
 @pytest.mark.parametrize("tool,argument_key,hf_repo,template_override", [
     (TEST_TOOL,    "success",  "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None),
     (PYTHON_TOOL,  "code",     "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None),
+    (PYTHON_TOOL,  "code",     "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", "chatml"),
+
+    # Note: gemma-2-2b-it knows itself as "model", not "assistant", so we don't test the ill-suited chatml on it.
     (TEST_TOOL,    "success",  "bartowski/gemma-2-2b-it-GGUF:Q4_K_M",              None),
     (PYTHON_TOOL,  "code",     "bartowski/gemma-2-2b-it-GGUF:Q4_K_M",              None),
+
     (TEST_TOOL,    "success",  "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M",      None),
     (PYTHON_TOOL,  "code",     "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M",      None),
+    (PYTHON_TOOL,  "code",     "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M",      "chatml"),
+
     (TEST_TOOL,    "success",  "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M",        None),
     (PYTHON_TOOL,  "code",     "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M",        None),
+    (PYTHON_TOOL,  "code",     "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M",        "chatml"),
+
     (TEST_TOOL,    "success",  "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
     (PYTHON_TOOL,  "code",     "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
+    (PYTHON_TOOL,  "code",     "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", "chatml"),
+
     (TEST_TOOL,    "success",  "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",   ("NousResearch/Hermes-3-Llama-3.1-8B", "tool_use")),
     (PYTHON_TOOL,  "code",     "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",   ("NousResearch/Hermes-3-Llama-3.1-8B", "tool_use")),
+    (PYTHON_TOOL,  "code",     "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",   "chatml"),
+
     (TEST_TOOL,    "success",  "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", None),
     (PYTHON_TOOL,  "code",     "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", None),
-    (TEST_TOOL,    "success",  "bartowski/functionary-small-v3.2-GGUF:Q8_0",       ("meetkai/functionary-medium-v3.2", None)),
+    (PYTHON_TOOL,  "code",     "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", "chatml"),
-    (PYTHON_TOOL,  "code",     "bartowski/functionary-small-v3.2-GGUF:Q8_0",       ("meetkai/functionary-medium-v3.2", None)),
+
+    (TEST_TOOL,    "success",  "bartowski/functionary-small-v3.2-GGUF:Q4_K_M",       ("meetkai/functionary-medium-v3.2", None)),
+    (PYTHON_TOOL,  "code",     "bartowski/functionary-small-v3.2-GGUF:Q4_K_M",       ("meetkai/functionary-medium-v3.2", None)),
+    (PYTHON_TOOL,  "code",     "bartowski/functionary-small-v3.2-GGUF:Q4_K_M",       "chatml"),
+
     (TEST_TOOL,    "success",  "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M",      ("meta-llama/Llama-3.2-3B-Instruct", None)),
     (PYTHON_TOOL,  "code",     "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M",      ("meta-llama/Llama-3.2-3B-Instruct", None)),
+    (PYTHON_TOOL,  "code",     "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M",      "chatml"),
+
     (TEST_TOOL,    "success",  "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M",      ("meta-llama/Llama-3.2-3B-Instruct", None)),
     (PYTHON_TOOL,  "code",     "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M",      ("meta-llama/Llama-3.2-3B-Instruct", None)),
+    (PYTHON_TOOL,  "code",     "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M",      "chatml"),
     # TODO: fix these
     # (TEST_TOOL,    "success",  "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None),
     # (PYTHON_TOOL,  "code",     "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None),
 ])
-def test_completion_with_required_tool_real_model(tool: dict, argument_key: str | None, hf_repo: str, template_override: Tuple[str, str | None] | None):
+def test_completion_with_required_tool_real_model(tool: dict, argument_key: str | None, hf_repo: str, template_override: str | Tuple[str, str | None] | None):
+    global server
     n_predict = 512
     server.n_slots = 1
     server.jinja = True
@@ -169,10 +189,12 @@ def test_completion_with_required_tool_real_model(tool: dict, argument_key: str
     server.n_predict = n_predict
     server.model_hf_repo = hf_repo
     server.model_hf_file = None
-    if template_override:
+    if isinstance(template_override, tuple):
         (template_hf_repo, template_variant) = template_override
         server.chat_template_file = f"../../../models/templates/{template_hf_repo.replace('/', '-') + ('-' + template_variant if template_variant else '')}.jinja"
         assert os.path.exists(server.chat_template_file), f"Template file {server.chat_template_file} does not exist. Run `python scripts/get_chat_template.py {template_hf_repo} {template_variant} > {server.chat_template_file}` to download the template."
+    elif isinstance(template_override, str):
+        server.chat_template = template_override
     server.start(timeout_seconds=TIMEOUT_SERVER_START)
     res = server.make_request("POST", "/chat/completions", data={
         "max_tokens": n_predict,
@@ -251,33 +273,55 @@ def test_completion_without_tool_call_slow(template_name: str, n_predict: int, t
 
 @pytest.mark.slow
 @pytest.mark.parametrize("hf_repo,template_override", [
+    ("bartowski/c4ai-command-r7b-12-2024-GGUF:Q4_K_M",   ("CohereForAI/c4ai-command-r7b-12-2024", "tool_use")),
     ("bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None),
-    ("bartowski/gemma-2-2b-it-GGUF:Q4_K_M",              None),
+    ("bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", "chatml"),
+
     ("bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M",      None),
+    ("bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M",      "chatml"),
+
     ("bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M",        None),
-    ("bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M", ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
+    ("bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M",        "chatml"),
-    ("bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",   ("NousResearch/Hermes-3-Llama-3.1-8B", "tool_use")),
+
+    ("bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M",    ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
+    ("bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M",    "chatml"),
+
+    ("bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",      ("NousResearch/Hermes-3-Llama-3.1-8B", "tool_use")),
+    ("bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",      "chatml"),
+
     ("bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", None),
+    ("bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", "chatml"),
+
     ("bartowski/functionary-small-v3.2-GGUF:Q8_0",       ("meetkai/functionary-medium-v3.2", None)),
+    ("bartowski/functionary-small-v3.2-GGUF:Q8_0",       "chatml"),
+
     ("bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M",      ("meta-llama/Llama-3.2-3B-Instruct", None)),
+    ("bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M",      "chatml"),
+
+    # Note: gemma-2-2b-it knows itself as "model", not "assistant", so we don't test the ill-suited chatml on it.
+    ("bartowski/gemma-2-2b-it-GGUF:Q4_K_M",              None),
+
     # ("bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M", ("meta-llama/Llama-3.2-3B-Instruct", None)),
     # ("bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None),
 ])
-def test_weather_tool_call(hf_repo: str, template_override: Tuple[str, str | None] | None):
+def test_weather(hf_repo: str, template_override: Tuple[str, str | None] | None):
     global server
+    n_predict = 512
     server.n_slots = 1
     server.jinja = True
     server.n_ctx = 8192
-    server.n_predict = 512
+    server.n_predict = n_predict
     server.model_hf_repo = hf_repo
     server.model_hf_file = None
-    if template_override:
+    if isinstance(template_override, tuple):
         (template_hf_repo, template_variant) = template_override
         server.chat_template_file = f"../../../models/templates/{template_hf_repo.replace('/', '-') + ('-' + template_variant if template_variant else '')}.jinja"
         assert os.path.exists(server.chat_template_file), f"Template file {server.chat_template_file} does not exist. Run `python scripts/get_chat_template.py {template_hf_repo} {template_variant} > {server.chat_template_file}` to download the template."
+    elif isinstance(template_override, str):
+        server.chat_template = template_override
     server.start(timeout_seconds=TIMEOUT_SERVER_START)
     res = server.make_request("POST", "/chat/completions", data={
-        "max_tokens": 256,
+        "max_tokens": n_predict,
         "messages": [
             {"role": "user", "content": "What is the weather in Istanbul?"},
         ],
@@ -298,19 +342,39 @@ def test_weather_tool_call(hf_repo: str, template_override: Tuple[str, str | Non
 
 @pytest.mark.slow
 @pytest.mark.parametrize("expected_arguments_override,hf_repo,template_override", [
-    (None,                 "bartowski/gemma-2-2b-it-GGUF:Q4_K_M",              None),
     (None,                 "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M",      None),
+    (None,                 "bartowski/Phi-3.5-mini-instruct-GGUF:Q4_K_M",      "chatml"),
+
     (None,                 "bartowski/functionary-small-v3.2-GGUF:Q8_0",       ("meetkai-functionary-medium-v3.2", None)),
-    ('{"code":"print("}',  "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None),
+    (None,                 "bartowski/functionary-small-v3.2-GGUF:Q8_0",       "chatml"),
-    (None,                 "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M",      ("meta-llama-Llama-3.2-3B-Instruct", None)),
+
+    (None,                 "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", None),
+    ('{"code":"print("}',  "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M", "chatml"),
+
+    ('{"code":"print("}',  "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M",      ("meta-llama-Llama-3.2-3B-Instruct", None)),
+    (None,                 "bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M",      "chatml"),
+
     ('{"code":"print("}',  "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M",      ("meta-llama-Llama-3.2-3B-Instruct", None)),
+    ('{"code":"print("}',  "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M",      "chatml"),
+
     (None,                 "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M",        None),
-    (None,                 "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M",      ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
+    (None,                 "bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M",        "chatml"),
-    (None,                 "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",   ("NousResearch-Hermes-3-Llama-3.1-8B", "tool_use")),
+
+    (None,                 "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M",    ("NousResearch/Hermes-2-Pro-Llama-3-8B", "tool_use")),
+    (None,                 "bartowski/Hermes-2-Pro-Llama-3-8B-GGUF:Q4_K_M",    "chatml"),
+
+    (None,                 "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",      ("NousResearch-Hermes-3-Llama-3.1-8B", "tool_use")),
+    (None,                 "bartowski/Hermes-3-Llama-3.1-8B-GGUF:Q4_K_M",      "chatml"),
+
     (None,                 "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", None),
+    (None,                 "bartowski/Mistral-Nemo-Instruct-2407-GGUF:Q4_K_M", "chatml"),
+
+    # Note: gemma-2-2b-it knows itself as "model", not "assistant", so we don't test the ill-suited chatml on it.
+    (None,                 "bartowski/gemma-2-2b-it-GGUF:Q4_K_M",              None),
+
     # (None,                 "bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q4_K_M", None),
 ])
-def test_hello_world_tool_call(expected_arguments_override: str | None, hf_repo: str, template_override: Tuple[str, str | None] | None):
+def test_hello_world_tool_call(expected_arguments_override: str | None, hf_repo: str, template_override: str | Tuple[str, str | None] | None):
     global server
     server.n_slots = 1
     server.jinja = True
@@ -318,10 +382,12 @@ def test_hello_world_tool_call(expected_arguments_override: str | None, hf_repo:
     server.n_predict = 128
     server.model_hf_repo = hf_repo
     server.model_hf_file = None
-    if template_override:
+    if isinstance(template_override, tuple):
         (template_hf_repo, template_variant) = template_override
         server.chat_template_file = f"../../../models/templates/{template_hf_repo.replace('/', '-') + ('-' + template_variant if template_variant else '')}.jinja"
         assert os.path.exists(server.chat_template_file), f"Template file {server.chat_template_file} does not exist. Run `python scripts/get_chat_template.py {template_hf_repo} {template_variant} > {server.chat_template_file}` to download the template."
+    elif isinstance(template_override, str):
+        server.chat_template = template_override
     server.start(timeout_seconds=TIMEOUT_SERVER_START)
     res = server.make_request("POST", "/chat/completions", data={
         "max_tokens": 256,

examples/server/utils.hpp

@@ -5,10 +5,6 @@
 #include "llama.h"
 #include "common/base64.hpp"
 
-#ifndef NDEBUG
-// crash the server in debug mode, otherwise send an http 500 error
-#define CPPHTTPLIB_NO_EXCEPTIONS 1
-#endif
 // increase max payload length to allow use of larger context size
 #define CPPHTTPLIB_FORM_URL_ENCODED_PAYLOAD_MAX_LENGTH 1048576
 #include "httplib.h"

examples/server/webui/index.html

@@ -154,8 +154,6 @@
             placeholder="Type a message (Shift+Enter to add a new line)"
             v-model="inputMsg"
             @keydown.enter.exact.prevent="sendMessage"
-            @keydown.enter.shift.exact.prevent="inputMsg += '\n'"
-            :disabled="isGenerating"
             id="msg-input"
             dir="auto"
           ></textarea>

examples/server/webui/src/main.js

@@ -468,7 +468,10 @@ const mainApp = createApp({
       URL.revokeObjectURL(url);
     },
     async sendMessage() {
-      if (!this.inputMsg) return;
+      // prevent sending empty message
+      // also allow typing the message while generating, but does not allow sending it (to match UX/UI behavior of other chat apps)
+      if (!this.inputMsg || this.isGenerating) return;
+
       const currConvId = this.viewingConvId;
 
       StorageUtils.appendMsg(currConvId, {

ggml/CMakeLists.txt

@@ -274,22 +274,25 @@ endif()
 
 # Generate version info based on git commit.
 
-find_program(GIT_EXE NAMES git git.exe REQUIRED NO_CMAKE_FIND_ROOT_PATH)
+if(NOT DEFINED GGML_BUILD_NUMBER)
-execute_process(COMMAND ${GIT_EXE} rev-list --count HEAD
+    find_program(GIT_EXE NAMES git git.exe REQUIRED NO_CMAKE_FIND_ROOT_PATH)
-    WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
+    execute_process(COMMAND ${GIT_EXE} rev-list --count HEAD
-    OUTPUT_VARIABLE GGML_BUILD_NUMBER
+        WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
-    OUTPUT_STRIP_TRAILING_WHITESPACE
+        OUTPUT_VARIABLE GGML_BUILD_NUMBER
-)
+        OUTPUT_STRIP_TRAILING_WHITESPACE
+    )
 
-if(GGML_BUILD_NUMBER EQUAL 1)
+    if(GGML_BUILD_NUMBER EQUAL 1)
-    message(WARNING "GGML build version fixed at 1 likely due to a shallow clone.")
+        message(WARNING "GGML build version fixed at 1 likely due to a shallow clone.")
+    endif()
+
+    execute_process(COMMAND ${GIT_EXE} rev-parse --short HEAD
+        WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
+        OUTPUT_VARIABLE GGML_BUILD_COMMIT
+        OUTPUT_STRIP_TRAILING_WHITESPACE
+    )
 endif()
 
-execute_process(COMMAND ${GIT_EXE} rev-parse --short HEAD
-    WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
-    OUTPUT_VARIABLE GGML_BUILD_COMMIT
-    OUTPUT_STRIP_TRAILING_WHITESPACE
-)
 
 # Capture variables prefixed with GGML_.
 

ggml/src/ggml-cuda/common.cuh

@@ -176,6 +176,14 @@ static constexpr bool new_mma_available(const int cc) {
     return cc < GGML_CUDA_CC_OFFSET_AMD && cc >= GGML_CUDA_CC_TURING;
 }
 
+static constexpr __device__ int ggml_cuda_get_physical_warp_size() {
+#if defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__)
+    return __AMDGCN_WAVEFRONT_SIZE;
+#else
+    return 32;
+#endif // defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__)
+}
+
 [[noreturn]]
 static __device__ void no_device_code(
     const char * file_name, const int line, const char * function_name, const int arch, const char * arch_list) {

ggml/src/ggml-cuda/fattn-common.cuh

@@ -516,6 +516,12 @@ constexpr __device__ dequantize_1_f32_t get_dequantize_1_f32(ggml_type type_V) {
         nullptr;
 }
 
+// The HIP compiler for some reason complains that it can't unroll a loop because of the jt*ncols + j >= ne01 conditional.
+#ifdef __clang__
+#pragma clang diagnostic push
+#pragma clang diagnostic ignored "-Wpass-failed"
+#endif // __clang__
+
 template<int D, int ncols, int KQ_stride> // D == head size
 #if !(defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__))
 __launch_bounds__(D, 1)
@@ -614,6 +620,10 @@ static __global__ void flash_attn_stream_k_fixup(
     }
 }
 
+#ifdef __clang__
+#pragma clang diagnostic pop
+#endif // __clang__
+
 template<int D, int parallel_blocks> // D == head size
 #if !(defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__))
 __launch_bounds__(D, 1)

ggml/src/ggml-cuda/fattn-wmma-f16.cu

@@ -561,7 +561,7 @@ void ggml_cuda_flash_attn_ext_wmma_f16(ggml_backend_cuda_context & ctx, ggml_ten
                     ggml_cuda_flash_attn_ext_wmma_f16_case<128, cols_per_block, float>(ctx, dst);
                     break;
                 // case 256:
-                //     ggml_cuda_flash_attn_ext_wmma_f16_case<128, cols_per_block, float>(ctx, dst);
+                //     ggml_cuda_flash_attn_ext_wmma_f16_case<256, cols_per_block, float>(ctx, dst);
                 //     break;
                 default:
                     GGML_ABORT("fatal error");

ggml/src/ggml-cuda/fattn.cu

@@ -235,7 +235,7 @@ void ggml_cuda_flash_attn_ext(ggml_backend_cuda_context & ctx, ggml_tensor * dst
         return;
     }
 
-    if (!new_mma_available(cc)) {
+    if (!fp16_mma_available(cc)) {
         if (prec == GGML_PREC_DEFAULT) {
             if (Q->ne[1] <= 8) {
                 ggml_cuda_flash_attn_ext_vec_f16(ctx, dst);
@@ -265,6 +265,7 @@ void ggml_cuda_flash_attn_ext(ggml_backend_cuda_context & ctx, ggml_tensor * dst
     // The MMA implementation needs Turing or newer, use the old WMMA code for Volta:
     if (cc == GGML_CUDA_CC_VOLTA) {
         ggml_cuda_flash_attn_ext_wmma_f16(ctx, dst);
+        return;
     }
 
     ggml_cuda_flash_attn_ext_mma_f16(ctx, dst);

ggml/src/ggml-cuda/mmv.cu

@@ -5,9 +5,10 @@ template <typename T, typename type_acc, int block_size>
 static __global__ void mul_mat_vec(
         const T * __restrict__ x, const float * __restrict__ y, float * __restrict__ dst, const int64_t ncols2, const int64_t stride_row,
         const int64_t channel_ratio, const int64_t stride_channel_x, const int64_t stride_channel_y, const int64_t stride_channel_dst) {
-    const int64_t row     = blockIdx.x;
+    const int64_t row       = blockIdx.x;
-    const int64_t channel = blockIdx.z;
+    const int64_t channel   = blockIdx.z;
-    const int     tid     = threadIdx.x;
+    const int     tid       = threadIdx.x;
+    constexpr int warp_size = ggml_cuda_get_physical_warp_size();
 
     x   += (channel/channel_ratio)*stride_channel_x + row*stride_row;
     y   +=  channel               *stride_channel_y;
@@ -18,8 +19,8 @@ static __global__ void mul_mat_vec(
     extern __shared__ char data_mmv[];
     float * buf_iw = (float *) data_mmv;
 
-    if (block_size > WARP_SIZE) {
+    if (block_size > warp_size) {
-        if (tid < WARP_SIZE) {
+        if (tid < warp_size) {
             buf_iw[tid] = 0.0f;
         }
         __syncthreads();
@@ -67,16 +68,16 @@ static __global__ void mul_mat_vec(
         static_assert(std::is_same<T, void>::value, "unsupported type");
     }
 
-    sumf = warp_reduce_sum(sumf);
+    sumf = warp_reduce_sum<warp_size>(sumf);
 
-    if (block_size > WARP_SIZE) {
+    if (block_size > warp_size) {
-        buf_iw[tid/WARP_SIZE] = sumf;
+        buf_iw[tid/warp_size] = sumf;
         __syncthreads();
-        if (tid >= WARP_SIZE) {
+        if (tid >= warp_size) {
             return;
         }
         sumf = buf_iw[tid];
-        sumf = warp_reduce_sum(sumf);
+        sumf = warp_reduce_sum<warp_size>(sumf);
     }
 
     if (tid != 0) {
@@ -96,10 +97,19 @@ static void launch_mul_mat_vec_cuda(
     GGML_ASSERT(stride_row % 2 == 0);
     GGML_ASSERT(nchannels_y % nchannels_x == 0);
     const int64_t channel_ratio = nchannels_y / nchannels_x;
+    int device;
+    int warp_size;
 
-    int64_t block_size_best = WARP_SIZE;
+    CUDA_CHECK(cudaGetDevice(&device));
-    int64_t niter_best      = (ncols + 2*WARP_SIZE - 1) / (2*WARP_SIZE);
+    warp_size = ggml_cuda_info().devices[device].warp_size;
-    for (int64_t block_size = 2*WARP_SIZE; block_size <= 256; block_size += WARP_SIZE) {
+
+    int64_t block_size_best = warp_size;
+    int64_t niter_best      = (ncols + 2*warp_size - 1) / (2*warp_size);
+    int64_t max_block_size  = 256;
+    if(ggml_cuda_info().devices[device].cc > GGML_CUDA_CC_OFFSET_AMD && ggml_cuda_info().devices[device].cc < GGML_CUDA_CC_RDNA1) {
+        max_block_size = 128;
+    }
+    for (int64_t block_size = 2*warp_size; block_size <= max_block_size; block_size += warp_size) {
         const int64_t niter = (ncols + 2*block_size - 1) / (2*block_size);
         if (niter < niter_best) {
             niter_best      = niter;
@@ -107,7 +117,7 @@ static void launch_mul_mat_vec_cuda(
         }
     }
 
-    const int smem = WARP_SIZE*sizeof(float);
+    const int smem = warp_size*sizeof(float);
     const dim3 block_nums(nrows, 1, nchannels_y);
     const dim3 block_dims(block_size_best, 1, 1);
     switch (block_size_best) {

ggml/src/ggml-cuda/softmax.cu

@@ -18,7 +18,7 @@ __device__ float __forceinline__ t2f32<half>(half val) {
 #ifdef __clang__
 #pragma clang diagnostic push
 #pragma clang diagnostic ignored "-Wpass-failed"
-#endif
+#endif // __clang__
 template <bool use_shared, int ncols_template, int block_size_template, typename T>
 static __global__ void soft_max_f32(
         const float * x, const T * mask, float * dst, const int ncols_par, const int nrows_y,
@@ -126,7 +126,7 @@ static __global__ void soft_max_f32(
 }
 #ifdef __clang__
 #pragma clang diagnostic pop
-#endif
+#endif // __clang__
 
 static __global__ void soft_max_back_f32(
         const float * grad, const float * dstf, float * dst, const int ncols, const float scale) {

ggml/src/ggml-cuda/vendors/hip.h

@@ -1,5 +1,6 @@
 #pragma once
 
+#define HIP_ENABLE_WARP_SYNC_BUILTINS 1
 #include <hip/hip_runtime.h>
 #include <hipblas/hipblas.h>
 #include <hip/hip_fp16.h>
@@ -8,6 +9,7 @@
 // for rocblas_initialize()
 #include "rocblas/rocblas.h"
 #endif // __HIP_PLATFORM_AMD__
+
 #define CUBLAS_COMPUTE_16F HIPBLAS_R_16F
 #define CUBLAS_COMPUTE_32F HIPBLAS_R_32F
 #define CUBLAS_COMPUTE_32F_FAST_16F HIPBLAS_R_32F

ggml/src/ggml-metal/ggml-metal.m

@@ -20,7 +20,10 @@
 #define GGML_METAL_MAX_COMMAND_BUFFERS 8
 
 // create residency sets only on macOS >= 15.0
-#if TARGET_OS_OSX && __MAC_OS_X_VERSION_MAX_ALLOWED >= 150000
+#if TARGET_OS_OSX && __MAC_OS_X_VERSION_MAX_ALLOWED >= 150000 || \
+    TARGET_OS_IOS && __IPHONE_OS_VERSION_MAX_ALLOWED >= 180000 || \
+    TARGET_OS_TV && __TV_OS_VERSION_MAX_ALLOWED >= 180000 || \
+    TARGET_OS_VISION && __VISION_OS_VERSION_MAX_ALLOWED >= 200000
 #define GGML_METAL_HAS_RESIDENCY_SETS 1
 #endif
 
@@ -1071,7 +1074,7 @@ static bool ggml_backend_metal_buffer_rset_init(
     }
 
 #if defined(GGML_METAL_HAS_RESIDENCY_SETS)
-    if (@available(macOS 15.0, *)) {
+    if (@available(macOS 15.0, iOS 18.0, tvOS 18.0, visionOS 2.0, *)) {
         MTLResidencySetDescriptor * desc = [[MTLResidencySetDescriptor alloc] init];
         desc.label = @"ggml_backend_metal";
         desc.initialCapacity = ctx->n_buffers;
@@ -1106,7 +1109,7 @@ static bool ggml_backend_metal_buffer_rset_init(
 // rset free
 static void ggml_backend_metal_buffer_rset_free(struct ggml_backend_metal_buffer_context * ctx) {
 #if defined(GGML_METAL_HAS_RESIDENCY_SETS)
-    if (@available(macOS 15.0, *)) {
+    if (@available(macOS 15.0, iOS 18.0, tvOS 18.0, visionOS 2.0, *)) {
         if (ctx->rset) {
             [ctx->rset endResidency];
             [ctx->rset removeAllAllocations];

scripts/sync-ggml.last

@@ -1 +1 @@
-32f0b85987396945afea2291d5f4c5862434292b
+694244a6e40dc255f6bb4376fb17431c06633e6c

tests/test-chat.cpp

@@ -289,7 +289,7 @@ static void test_template(const common_chat_template & tmpl, const std::vector<s
 static void test_template_output_parsers() {
     json text_message {
         { "role",    "assistant"     },
-        { "content", "Hello, world!" },
+        { "content", "Hello, world!\nWhat's up?" },
     };
     json tool_calls = json::array({{
         { "type", "function" },
@@ -379,7 +379,7 @@ static void test_template_output_parsers() {
 
     common_chat_inputs inputs_no_tools;
     inputs_no_tools.messages = {
-        { { "role", "user" }, { "content", "Hey" } }
+        { { "role", "user" }, { "content", "Hey\nThere" } }
     };
 
     common_chat_inputs inputs_tools = inputs_no_tools;
@@ -408,7 +408,8 @@ static void test_template_output_parsers() {
                       "    {\"tool_call_id\": \"0\", \"tool_name\": \"special_function\", \"parameters\": {\"arg1\": 1}}\n"
                       "]<|END_ACTION|>");
         test_template(tmpl, end_tokens, text_message, tools,
-                      "<|START_RESPONSE|>Hello, world!<|END_RESPONSE|>",
+                      "<|START_RESPONSE|>Hello, world!\n"
+                      "What's up?<|END_RESPONSE|>",
                       /* expect_grammar_triggered= */ false);
     }
     {
@@ -428,7 +429,7 @@ static void test_template_output_parsers() {
 
         assert_msg_equals(msg_from_json(text_message),
                           common_chat_parse("{\n"
-                                            "  \"response\": \"Hello, world!\"\n"
+                                            "  \"response\": \"Hello, world!\\nWhat's up?\"\n"
                                             "}",
                                             common_chat_params_init(tmpl, inputs_tools).format));
         test_template(tmpl, end_tokens, tool_call_message_with_id, tools,
@@ -451,7 +452,7 @@ static void test_template_output_parsers() {
 
         assert_equals(COMMON_CHAT_FORMAT_MISTRAL_NEMO, common_chat_params_init(tmpl, inputs_tools).format);
 
-        test_template(tmpl, end_tokens, text_message, tools, "Hello, world!", /* expect_grammar_triggered= */ false);
+        test_template(tmpl, end_tokens, text_message, tools, "Hello, world!\nWhat's up?", /* expect_grammar_triggered= */ false);
         test_template(
             tmpl, end_tokens, tool_call_message_with_id, tools,
             "[TOOL_CALLS][{\"name\": \"special_function\", \"arguments\": {\"arg1\": 1}, \"id\": \"123456789\"}]");
@@ -476,7 +477,7 @@ static void test_template_output_parsers() {
                 inputs_tools)
                 .format);
 
-        test_template(tmpl, end_tokens, text_message, tools, "Hello, world!", /* expect_grammar_triggered= */ false);
+        test_template(tmpl, end_tokens, text_message, tools, "Hello, world!\nWhat's up?", /* expect_grammar_triggered= */ false);
         test_template(tmpl, end_tokens, tool_call_message, tools,
                       "<tool_call>\n"
                       "{\"name\": \"special_function\", \"arguments\": {\"arg1\": 1}}\n"
@@ -516,7 +517,7 @@ static void test_template_output_parsers() {
 
         assert_equals(COMMON_CHAT_FORMAT_LLAMA_3_X, common_chat_params_init(tmpl, inputs_tools).format);
 
-        test_template(tmpl, end_tokens, text_message, tools, "Hello, world!", /* expect_grammar_triggered= */ false);
+        test_template(tmpl, end_tokens, text_message, tools, "Hello, world!\nWhat's up?", /* expect_grammar_triggered= */ false);
         test_template(tmpl, end_tokens, tool_call_message, tools,
                       "{\"name\": \"special_function\", \"parameters\": {\"arg1\": 1}}");
     }
@@ -528,7 +529,7 @@ static void test_template_output_parsers() {
         assert_equals(COMMON_CHAT_FORMAT_FUNCTIONARY_V3_1_LLAMA_3_1,
                       common_chat_params_init(tmpl, inputs_tools).format);
 
-        test_template(tmpl, end_tokens, text_message, tools, "Hello, world!", /* expect_grammar_triggered= */ false);
+        test_template(tmpl, end_tokens, text_message, tools, "Hello, world!\nWhat's up?", /* expect_grammar_triggered= */ false);
         test_template(tmpl, end_tokens, tool_call_message, tools,
                       "<function=special_function>{\"arg1\": 1}</function>");
     }
@@ -542,7 +543,8 @@ static void test_template_output_parsers() {
 
         test_template(tmpl, end_tokens, text_message, {},
                       "all\n"
-                      "Hello, world!",
+                      "Hello, world!\n"
+                      "What's up?",
                       /* expect_grammar_triggered= */ false);
         test_template(tmpl, end_tokens, tool_call_message, tools,
                       "special_function\n"
@@ -555,7 +557,7 @@ static void test_template_output_parsers() {
 
         assert_equals(COMMON_CHAT_FORMAT_FIREFUNCTION_V2, common_chat_params_init(tmpl, inputs_tools).format);
 
-        test_template(tmpl, end_tokens, text_message, tools, "Hello, world!", /* expect_grammar_triggered= */ false);
+        test_template(tmpl, end_tokens, text_message, tools, "Hello, world!\nWhat's up?", /* expect_grammar_triggered= */ false);
         test_template(tmpl, end_tokens, tool_call_message, tools,
                       " functools[{\"name\": \"special_function\", \"arguments\": {\"arg1\": 1}}]");
     }
@@ -566,7 +568,7 @@ static void test_template_output_parsers() {
 
         assert_equals(COMMON_CHAT_FORMAT_DEEPSEEK_R1, common_chat_params_init(tmpl, inputs_tools).format);
 
-        test_template(tmpl, end_tokens, text_message, tools, "Hello, world!", /* expect_grammar_triggered= */ false);
+        test_template(tmpl, end_tokens, text_message, tools, "Hello, world!\nWhat's up?", /* expect_grammar_triggered= */ false);
         test_template(tmpl, end_tokens, tool_call_message, tools,
                       "<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>function<｜tool▁sep｜>special_function\n"
                       "```json\n"