Commit graph

  • 6c318b54c8
    Update README.md Yazan Agha-Schrader 2023-11-27 18:28:32 +01:00
  • ecb39732e6 add min-p image Yazan Agha-Schrader 2023-11-27 18:25:17 +01:00
  • 082b33550f
    Update README.md Yazan Agha-Schrader 2023-11-27 18:19:26 +01:00
  • c48f3f2042
    Merge pull request #3 from mounta11n/server-ui-improvements Yazan Agha-Schrader 2023-11-27 17:58:23 +01:00
  • 464f073307 add min-p Yazan Agha-Schrader 2023-11-27 17:56:30 +01:00
  • d55b482361
    Merge pull request #2 from mounta11n/server-ui-improvements Yazan Agha-Schrader 2023-11-27 17:26:43 +01:00
  • 809b2697fe
    Merge branch 'ggerganov:master' into master Yazan Agha-Schrader 2023-11-27 17:24:35 +01:00
  • c161ad20db add mmproj function Yazan Agha-Schrader 2023-11-27 17:17:38 +01:00
  • d5683279b1 fix wrong translation Yazan Agha-Schrader 2023-11-27 16:19:08 +01:00
  • bb03290c17
    examples : iOS example with swift ui (#4159) b1571 Bailey Chittle 2023-11-27 09:56:52 -05:00
  • 164ae84edf formatting with printf mike dupont 2023-11-27 09:56:23 -05:00
  • 09e3b50f62 fix wrong formattings Yazan Agha-Schrader 2023-11-27 15:54:21 +01:00
  • 3cd807d000 working better mike dupont 2023-11-27 09:48:55 -05:00
  • af05571d23
    Update .github/workflows/build.yml Bailey Chittle 2023-11-27 09:32:54 -05:00
  • cf8cb0d303 fix multi-modal-selection Yazan Agha-Schrader 2023-11-27 15:05:10 +01:00
  • 49d7c07210
    Update README.md Yazan Agha-Schrader 2023-11-27 14:23:51 +01:00
  • 1bb2df7367
    Update README.md Yazan Agha-Schrader 2023-11-27 14:22:31 +01:00
  • 25ed0c4f6b add ui and tui pics Yazan Agha-Schrader 2023-11-27 14:18:39 +01:00
  • 1bc9ca6a9c add ui and tui pics Yazan Agha-Schrader 2023-11-27 14:17:04 +01:00
  • a28935febe
    Update README.md Yazan Agha-Schrader 2023-11-27 14:14:46 +01:00
  • ca22eb6cc7
    Merge pull request #1 from mounta11n/server-ui-improvements Yazan Agha-Schrader 2023-11-27 14:11:48 +01:00
  • e7cfe1f5d9 add favicon Yazan Agha-Schrader 2023-11-27 13:58:54 +01:00
  • 2f0ae316f6
    Update CMakeLists.txt Georgi Gerganov 2023-11-27 14:49:03 +02:00
  • 9abb31011b
    Update index.html Yazan Agha-Schrader 2023-11-27 13:47:08 +01:00
  • 7ac56bdc62 now crashing mike dupont 2023-11-27 07:30:23 -05:00
  • 4d15130fda add start script Yazan Agha-Schrader 2023-11-27 13:06:27 +01:00
  • 0e5f16de53 reduce max ctx to fit instead of crashing Concedo 2023-11-27 19:08:54 +08:00
  • 2566e53945 ic Yazan Agha-Schrader 2023-11-27 11:33:06 +01:00
  • c830a0537b
    Merge branch 'master' into cuda-cublas-opts Georgi Gerganov 2023-11-27 11:49:14 +02:00
  • 8acd7be734 Merge branch 'master' into concedo_experimental Concedo 2023-11-27 14:06:14 +08:00
  • ec1796bec1 updated lite Concedo 2023-11-27 14:04:53 +08:00
  • b39ae69555 feat(ci): add an option to fail on compile warning ananta 2023-11-05 18:24:55 -05:00
  • f3b269813f
    ggml : fix -Warray-bounds warning with gcc (#4231) b1570 Jared Van Bortel 2023-11-26 22:58:43 -05:00
  • 12fb1c58ec cuda : tweak mm stride to double perf on P40 + GTX 970 Jared Van Bortel 2023-11-26 22:20:18 -05:00
  • 5906fb442b * more cleanup ziadb 2023-11-26 22:38:29 -05:00
  • ff67c764c4 * cleanup ziadb 2023-11-26 22:36:19 -05:00
  • 09562678d9 * add multiprompt support ziadb 2023-11-26 22:28:59 -05:00
  • d85b9bfed6 ggml : fix -Warray-bounds warning with gcc Jared Van Bortel 2023-11-26 21:49:48 -05:00
  • d86d5c55f5 Add Amica to UI list Kasumi Null 2023-11-27 10:47:57 +08:00
  • 77f4b996ed working mike dupont 2023-11-24 19:09:19 -05:00
  • b484674707 wip mike dupont 2023-11-26 19:31:56 -05:00
  • 1ec3f29bd0 Merge branch 'master' of github.com:ggerganov/llama.cpp Laura 2023-11-27 00:18:48 +01:00
  • f07f3ff61f now sampling lots of data mike dupont 2023-11-26 16:23:28 -05:00
  • 3e73d31d9c
    lookahead : support -n -1 infinite generation b1569 Georgi Gerganov 2023-11-26 21:51:46 +02:00
  • 9656026b53
    readme : update hot topics Georgi Gerganov 2023-11-26 20:42:51 +02:00
  • 922754a8d6
    lookahead : add example for lookahead decoding (#4207) b1567 Georgi Gerganov 2023-11-26 20:33:07 +02:00
  • 2f51a6afd5 trigger quiet mode when selecting remotetunnel Concedo 2023-11-27 00:16:36 +08:00
  • bffa78116d explore quiet mode Concedo 2023-11-26 23:57:27 +08:00
  • a6eb9b8010 Fix GPT2 not loading due to graph too small Concedo 2023-11-26 23:06:42 +08:00
  • 256478a97e attempt a llama.swiftui workflow Bailey Chittle 2023-11-26 11:17:08 +00:00
  • 777871703d typeinfo\n\nnow printing out some type information (ugly) for each field, more work needed mike dupont 2023-11-26 08:23:15 -05:00
  • 8d8b76d469
    lookahead : add comments lookahead Georgi Gerganov 2023-11-26 11:26:55 +02:00
  • 1a07a33939
    lookahead : fix a bug in the seq_id of the lookahead tokens Georgi Gerganov 2023-11-26 11:26:43 +02:00
  • fc63f88800 Implement further ops, rework op_f32 calls, fix bugs 0cc4m 2023-11-26 10:09:53 +01:00
  • 22da05536f
    metal : fix yarn (#4220) b1566 Xiao-Yong Jin 2023-11-26 02:30:02 -06:00
  • 7d50de2de1 lookahead : add to Makefile slaren 2023-11-26 08:33:11 +01:00
  • ec2b03e504 now printing tensors mike dupont 2023-11-25 20:06:00 -05:00
  • 1ddb52ec38
    scripts : Use mmap in torch load (#4202) Galunid 2023-11-25 22:45:02 +01:00
  • 32f7d6040f metal: fix yarn Xiao-Yong Jin 2023-11-25 15:42:27 -06:00
  • ee073086c5 fix current workflow errors Bailey Chittle 2023-11-25 13:16:14 -05:00
  • af698c6f27 now printing tokens mike dupont 2023-11-25 13:02:51 -05:00
  • f837c3a992
    llama : grammar reserve space in decode_utf8 (#4210) b1564 Marcus Dunn 2023-11-25 08:58:23 -08:00
  • 90568a6696 now server has it mike dupont 2023-11-25 11:13:45 -05:00
  • fc9e6ae25a
    Merge branch 'ggerganov:master' into master Li Tan 2023-11-25 07:50:46 -08:00
  • 3014b5415d
    Update docs for yarn_ext_factor <0.0 as unspecified instead of NaN (#4189) b1563 crasm 2023-11-25 10:47:07 -05:00
  • 7bd1cd7ef4
    lookahead : use deterministic init Georgi Gerganov 2023-11-25 17:12:16 +02:00
  • 6eb5166e5a
    lookahead : filter repeating n-grams Georgi Gerganov 2023-11-25 17:02:56 +02:00
  • 61d039727a
    lookahead : initial working implementation Georgi Gerganov 2023-11-25 16:25:38 +02:00
  • e8e94f4f69 working mike dupont 2023-11-25 09:25:19 -05:00
  • 9fb2c73bc0 adding include for refl mike dupont 2023-11-25 09:11:40 -05:00
  • bf019ef125 adding print statements to main. mike dupont 2023-11-25 09:11:20 -05:00
  • f067d52bea Naming the unnamed ggml structures mike dupont 2023-11-25 09:09:00 -05:00
  • 3faef69427 still not working mike dupont 2023-11-24 19:09:19 -05:00
  • 1b2e0bc3e6
    lookahead : use loop instead recursion to generate n-grams Georgi Gerganov 2023-11-25 13:58:41 +02:00
  • eb03b9ad69
    lookahead : generate and store n-grams Georgi Gerganov 2023-11-25 13:54:07 +02:00
  • 04814e718e
    readme : update hot topics Georgi Gerganov 2023-11-25 12:02:13 +02:00
  • af19d35734
    server : OAI API compatibility (#4198) b1561 Georgi Gerganov 2023-11-25 11:29:06 +02:00
  • a514a7af08
    Update README.md Miwa / Ensan 2023-11-25 14:41:57 +09:00
  • 3cc9682681 terminology. marcus 2023-11-24 20:50:30 -08:00
  • c788d1b579 added docs marcus 2023-11-24 20:49:58 -08:00
  • f29add56d8 changed allowed saving of pieces to reduce calls to llama_token_to_piece marcus 2023-11-24 20:47:01 -08:00
  • 54e41c895a fix the metal file foder path Li Tan 2023-11-24 18:55:52 -08:00
  • ea5178c2f1
    Add finetune option to the docker image. Juraj Bednar 2023-11-25 02:45:02 +01:00
  • 9d3ba0bacd improvement for the appended 0 marcus 2023-11-24 17:27:18 -08:00
  • a4b7b4c398
    Merge branch 'ggerganov:master' into master Marcus Dunn 2023-11-24 16:32:11 -08:00
  • 2e5c8aeab0 reserve space for codepoints marcus 2023-11-24 16:29:58 -08:00
  • 7c517e1722
    lookahead : init Georgi Gerganov 2023-11-24 16:47:21 +02:00
  • 1e275de79b now the debug print is working mike dupont 2023-11-24 14:15:07 -05:00
  • 62444fc812 Merge branch 'master' of https://github.com/FSSRepo/llama.cpp FSSRepo 2023-11-24 12:49:20 -05:00
  • b13911f02c add enough padding for alignment FSSRepo 2023-11-24 12:48:32 -05:00
  • e9c13ff781
    llama : set metal log callback correctly (#4204) b1560 slaren 2023-11-24 18:10:01 +01:00
  • 8a052c131e
    ggml-cuda : support stablelm rope (#4156) b1559 slaren 2023-11-24 18:04:31 +01:00
  • bc0fabfd98
    Merge branch 'ggerganov:master' into master Steward Garcia 2023-11-24 12:01:59 -05:00
  • 5ed3e1a8f2
    llama : fix llm_build_k_shift args Georgi Gerganov 2023-11-24 18:58:03 +02:00
  • bce88f20ed llama : set metal log callback correctly slaren 2023-11-24 17:56:58 +01:00
  • f4f0b06a9c add missing kernels FSSRepo 2023-11-24 11:55:30 -05:00
  • bc3b93b942 now starting to refactor the code mike dupont 2023-11-24 11:49:09 -05:00
  • 21b70babf7 straightforward /v1/models endpoint server-oai-compat Tobi Lütke 2023-11-24 11:22:39 -05:00
  • a5b7d7277e Merge branch 'master' into feat-override-metadata KerfuffleV2 2023-11-24 08:31:31 -07:00
  • 0f73d87dbe Revert .bin > .safetensors preference Galunid 2023-11-24 16:12:47 +01:00