vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
1848 commits 380 branches 3056 tags 365 MiB
Commit graph

1848 commits

This branch
This branch
All branches
Author SHA1 Message Date
Concedo
159ad9269d up ver, set the cuda pool malloc lookahead back to 5% instead of 2% (+1 squashed commits) 
Squashed commits:

[e0f65278] up ver, set the cuda pool malloc lookahead back to 5% instead of 2%
 2023-08-09 12:06:42 +08:00
Concedo
926d90fbab Merge branch 'master' into concedo_experimental 
# Conflicts:
#	Makefile
 2023-08-09 01:09:04 +08:00
Concedo
793cfd136c fixed 70B detection again, try fix horde issues, fixed lite unicode issue, fixed cmake for cuda 2023-08-09 01:05:00 +08:00
Martin Krasser
f5bfea0580
Allow passing grammar to completion endpoint (#2532) 
* Allow passing grammar to completion endpoint
 2023-08-08 16:29:19 +03:00
Johannes Gäßler
acfc5478ff
CUDA: tighter VRAM scratch size for 65b/70b (#2551) 2023-08-08 14:38:16 +02:00
chaihahaha
7ed8d1fe7f
llm.vim : multiline autocompletion, get rid of "^@" (#2543) 2023-08-08 15:07:02 +03:00
Georgi Gerganov
e7f94d6fdc
vim : bring back simple llm.vim example 2023-08-08 15:06:18 +03:00
AustinMroz
2d7baaf50f
vim : streaming and more (#2495) 
* Update Vim plugin

* Remove getbufoneline usage, Add input bind example.

getbufoneline() appears to be a recently added function and has been
replaced with getbufline for compatibility.

An additional example that explains how to add a keybind that works in
insert mode was added.
 2023-08-08 14:44:48 +03:00
klosax
f3c3b4b167
Add --rope-scale parameter (#2544) 
* common.cpp : Add --rope-scale parameter
* README.md : Add info about using linear rope scaling
 2023-08-07 19:07:19 +02:00
Concedo
3554080502 fixed blasbatchmul multiplier 2023-08-08 00:41:02 +08:00
Concedo
28ad80b6e4 Merge branch 'master' into concedo_experimental 2023-08-08 00:34:10 +08:00
Concedo
3c7d938d95 update lite, resize scratch buffers for blasbatch 2048 2023-08-08 00:32:51 +08:00
Georgi Gerganov
93356bdb7a
ggml : mul mat tweaks (#2372) 
* ggml : mul mat wip

ggml-ci

* ggml : alternative thread distribution for mul_mat

ggml-ci

* ggml : mul_mat block tiling attempt

* ggml : mul_mat threads yield

ggml-ci
 2023-08-07 14:25:58 +03:00
Georgi Gerganov
60baff7c85
ggml : pad result of ggml_nbytes() 2023-08-07 14:24:42 +03:00
Georgi Gerganov
9082b5dfbf
ggml : change params pointer (style change) (#2539) 
ggml-ci
 2023-08-07 13:55:18 +03:00
Georgi Gerganov
99d29c0094
ggml : sync (custom ops) (#2537) 
ggml-ci
 2023-08-07 13:20:09 +03:00
Concedo
9133e456d2 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	Makefile
#	build.zig
 2023-08-07 17:33:42 +08:00
Concedo
cae6a847ad cuda free only for non mmq (+2 squashed commit) 
Squashed commit:

[3aca763a] only cuda free for non mmq

[e69a8c9f] revert to pool alloc to try again
 2023-08-07 17:12:05 +08:00
Johannes Gäßler
3d9a551816
Fixed mmap prefetch for GPU offloading (#2529) 2023-08-07 10:09:40 +02:00
Georgi Gerganov
f6f9896ac3
metal : fix out-of-bounds access + inc concurrency nodes (#2416) 
* metal : fix out-of-bounds access + style changes

* metal : increase concurrency nodes to 2*GGML_MAX_NODES
 2023-08-07 10:52:57 +03:00
Concedo
9f16a4c4ef switch to upstream implementation of pool malloc 2023-08-07 15:16:37 +08:00
GiviMAD
34a14b28ff
[Makefile] Move ARM CFLAGS before compilation (#2536) 2023-08-07 09:21:46 +03:00
Henri Vasserman
7297128db8
[Zig] Rewrite build for Zig 0.11 (#2514) 
* zig build fixes

* Disable LTO on Windows.
 2023-08-07 08:35:53 +03:00
Concedo
6659652c9f lower actual temp used when temp=0 2023-08-07 11:05:06 +08:00
Concedo
0e41b94f40 improve detection for 70B. 2023-08-07 10:43:06 +08:00
Concedo
fb44d72a78 Merge remote-tracking branch 'johannes/cuda-fix-mmap-prefetch' into concedo_experimental 2023-08-07 10:17:43 +08:00
Concedo
559c0e2d1f updated lite again, fix for wi 2023-08-07 10:15:20 +08:00
JohannesGaessler
d9024df759 Fixed mmap prefetch for GPU offloading 2023-08-06 20:28:16 +02:00
Concedo
d442888626 Merge branch 'master' into concedo_experimental 
# Conflicts:
#	Makefile
 2023-08-06 22:47:33 +08:00
Concedo
198cc826fc updated lite 2023-08-06 22:19:18 +08:00
Concedo
e99416cdfe blasbatchsize 2023-08-06 17:47:59 +08:00
Concedo
bcfdd0e662 fixed bbs -1 and allow bbs = 2048 2023-08-06 17:47:05 +08:00
DannyDaemonic
86c3219895
console : fix issue related to Windows 11 PowerShell console mode persistence (#2521) 2023-08-06 09:49:34 +03:00
Keiichi Tabata
2e8265ae17
convert.py : add missing abstract methods for quantized data (#2491) 2023-08-06 09:34:05 +03:00
Johannes Gäßler
f514d1b306
CUDA: faster k-quant mul_mat_q kernels (#2525) 2023-08-05 18:20:44 +02:00
Jonas Wunderlich
332311234a
fix firefox autoscroll (#2519) 2023-08-04 22:16:11 +02:00
Cebtenzzre
182af739c4
server: regenerate completion.js.hpp (#2515) 2023-08-04 21:00:57 +02:00
Cebtenzzre
4329d1acb0
CUDA: use min compute capability of GPUs actually used (#2506) 2023-08-04 17:35:22 +02:00
Cebtenzzre
02f9d96a86
CUDA: check if event is NULL before cudaStreamWaitEvent (#2505) 
Fixes #2503
 2023-08-04 17:34:32 +02:00
DannyDaemonic
3498588e0f
Add --simple-io option for subprocesses and break out console.h and cpp (#1558) 2023-08-04 08:20:12 -07:00
Concedo
18bb0ab127 up ver, support 16k ctx 2023-08-04 21:47:17 +08:00
Stephen Nichols
5f631c2679
Fixing race condition in server and partial stream handling in frontend. (#2391) 
* Fixing race condition in server.cpp and partial stream handling in completion.js

* Reverting assert edits.

* Adding newline to eof
 2023-08-04 13:37:24 +02:00
l3utterfly
415e99fec2
Stream save llama context data to file instead of allocating entire buffer upfront (#2488) 
* added stream saving context data to file to avoid allocating unnecessary amounts of memory

* generalised copying state data to file or buffer

* added comments explaining how copy_state_data works

* fixed trailing whitespaces

* fixed save load state example

* updated save load state to use public function in llama.cpp

* - restored breakage of the llama_copy_state_data API
- moved new logic for copying llama state data to internal function

* fixed function declaration order

* restored save load state example

* fixed whitepace

* removed unused llama-util.h include

* Apply suggestions from code review

Co-authored-by: slaren <slarengh@gmail.com>

* Apply code review suggestions

Co-authored-by: slaren <slarengh@gmail.com>

---------

Co-authored-by: slaren <slarengh@gmail.com>
 2023-08-04 13:29:52 +02:00
Borislav Stanimirov
ff966e7ca6
build : fix several cast and printf warnings (#2499) 2023-08-04 13:07:21 +03:00
Concedo
f0764c6cfb fix indentation, increase server thread count 2023-08-04 10:29:56 +08:00
Concedo
d09e54aad1 Merge remote-tracking branch 'duncan/api-stream-double-write-fix' into concedo_experimental 2023-08-04 10:22:53 +08:00
duncannah
63ec711a70
fix: still send full result after streaming 2023-08-03 14:35:43 +02:00
Concedo
4709545c06 Merge remote-tracking branch 'duncan/api-stream-double-write-fix' into concedo_experimental 2023-08-03 12:52:43 +08:00
Concedo
ba2040d1df compile fix for ARM NEON 2023-08-03 12:52:06 +08:00
Concedo
3fa6befdaf increase max free blocks 2023-08-03 10:50:16 +08:00