Commit Graph

  • bee938da74
    nix: remove nixConfig from flake.nix (#4984) Philip Taron 2024-01-16 09:56:21 -08:00
  • cec8a48470
    finetune : add training data file to log message (#4979) Daniel Bevenius 2024-01-16 18:54:24 +01:00
  • 334a835a1c
    ggml : importance matrix support for legacy quants (#4969) Kawrakow 2024-01-16 19:51:26 +02:00
  • 4feb4b33ee
    examples : add complete parallel function calling example (#4974) Maximilian Winter 2024-01-16 18:41:42 +01:00
  • 959ef0c0df
    perplexity : fix kv cache handling for hellaswag (#4981) Georgi Gerganov 2024-01-16 19:34:54 +02:00
  • c37b3474e6
    flake.lock: update flake-parts, flake-parts/nixpkgs-lib, and nixpkgs (#4920) Georgi Gerganov 2024-01-16 19:13:54 +02:00
  • 158f8c9e21
    metal : localized logic in ggml_metal_graph_compute (#4924) Paul Tsochantaris 2024-01-16 17:05:19 +00:00
  • 862f5e41ab
    android : introduce starter project example (#4926) Neuman Vong 2024-01-17 00:47:34 +11:00
  • 3a48d558a6
    metal : replace loop of dispatch_async with dispatch_apply (#4934) Alex Azarov 2024-01-16 14:41:27 +01:00
  • 7c8d3abd1a
    metal : log recommendedMaxWorkingSetSize on iOS 16+ (#4936) Alex Azarov 2024-01-16 14:33:02 +01:00
  • 122ed4840c
    examples : fix and improv docs for the grammar generator (#4909) Maximilian Winter 2024-01-16 13:10:48 +01:00
  • a0b3ac8c48
    ggml : introduce GGML_CALL function annotation (#4850) Justine Tunney 2024-01-16 03:16:33 -08:00
  • d75c232e1d
    finetune : use LLAMA_FILE_MAGIC_GGLA (#4961) Daniel Bevenius 2024-01-16 12:14:19 +01:00
  • e0324285a5
    speculative : threading options (#4959) stduhpf 2024-01-16 12:04:32 +01:00
  • 3e5ca7931c
    pass cpu-architecture arguments only to host code (C;C++) (#4943) ngc92 2024-01-15 20:40:48 +02:00
  • 4483396751
    llama : apply classifier-free guidance to logits directly (#4951) David Friehs 2024-01-15 14:06:52 +01:00
  • d9aa4ffa6e
    awq-py : fix typo in awq-py/README.md (#4947) Victor Z. Peng 2024-01-15 04:41:46 -08:00
  • ddb008d845
    cuda : fix dequantize kernel names (#4938) Georgi Gerganov 2024-01-15 13:27:00 +02:00
  • 2faaef3979
    llama : check for 256 divisibility for IQ2_XS, IQ2_XXS (#4950) Kawrakow 2024-01-15 10:09:38 +02:00
  • 4a3156de2f
    CUDA: faster dequantize kernels for Q4_0 and Q4_1 (#4938) Kawrakow 2024-01-15 07:48:06 +02:00
  • a836c8f534
    llama : fix missing quotes (#4937) David Pflug 2024-01-14 10:46:00 -05:00
  • 467a882fd2
    Add ability to use importance matrix for all k-quants (#4930) Kawrakow 2024-01-14 16:21:12 +02:00
  • bb0c139247
    llama : check LLAMA_TRACE env for extra logging (#4929) Georgi Gerganov 2024-01-14 13:26:53 +02:00
  • 9408cfdad6
    scripts : sync-ggml-am.sh option to skip commits Georgi Gerganov 2024-01-14 11:08:09 +02:00
  • 03c5267490
    llama : use LLAMA_LOG_ macros for logging Georgi Gerganov 2024-01-14 11:03:19 +02:00
  • a128c38de8
    Fix ffn_down quantization mix for MoE models (#4927) Kawrakow 2024-01-14 10:53:39 +02:00
  • 5f5fe1bd60
    metal : correctly set SIMD support flags on iOS (#4923) Alex Azarov 2024-01-14 09:44:39 +01:00
  • ac32902a87
    llama : support WinXP build with MinGW 8.1.0 (#3419) Karthik Kumar Viswanathan 2024-01-14 00:41:44 -08:00
  • 147b17ac94
    2-bit quantizations (#4897) Kawrakow 2024-01-14 09:45:56 +02:00
  • 807179ec58
    Make Q3_K_S be the same as olf Q3_K_L for Mixtral-8x7B (#4906) Kawrakow 2024-01-14 09:44:30 +02:00
  • 76484fbfd3
    sync : ggml Georgi Gerganov 2024-01-14 00:14:46 +02:00
  • c71d608ce7
    ggml: cache sin/cos for RoPE (#4908) Johannes Gäßler 2024-01-13 21:41:37 +01:00
  • 4be5ef556d
    metal : remove old API (#4919) Georgi Gerganov 2024-01-13 20:45:45 +02:00
  • 0ea069b87b
    server : fix prompt caching with system prompt (#4914) Georgi Gerganov 2024-01-13 19:31:26 +02:00
  • f172de03f1
    llama : fix detokenization of non-special added-tokens (#4916) Georgi Gerganov 2024-01-13 18:47:38 +02:00
  • 2d57de5255
    metal : disable log for loaded kernels (#4794) Georgi Gerganov 2024-01-13 18:46:37 +02:00
  • df845cc982
    llama : minimize size used for state save/load (#4820) David Friehs 2024-01-13 17:29:43 +01:00
  • 6b48ed0893
    workflows: unbreak nix-build-aarch64, and split it out (#4915) Someone 2024-01-13 16:29:16 +00:00
  • 722d33f34e
    main : add parameter --no-display-prompt (#4541) Yann Follet 2024-01-14 00:09:08 +08:00
  • c30b1ef39a
    gguf : fix potential infinite for-loop (#4600) texmex76 2024-01-13 17:06:20 +01:00
  • b38b5e93ae
    metal : refactor kernel loading code (#4794) Georgi Gerganov 2024-01-13 18:03:45 +02:00
  • 7dc78764e2
    compare-llama-bench: tweak output format (#4910) Johannes Gäßler 2024-01-13 15:52:53 +01:00
  • 356327feb3
    server : fix deadlock that occurs in multi-prompt scenarios (#4905) Ziad Ben Hadj-Alouane 2024-01-13 09:20:46 -05:00
  • ee8243adaa
    server : fix crash with multimodal models without BOS token (#4904) makomk 2024-01-13 14:16:11 +00:00
  • 15ebe59210
    convert : update phi-2 to latest HF repo (#4903) Georgi Gerganov 2024-01-13 13:44:37 +02:00
  • de473f5f8e
    sync : ggml Georgi Gerganov 2024-01-12 22:02:43 +02:00
  • f238461236
    ggml : fix 32-bit ARM compat for IQ2_XS (whisper/1758) Georgi Gerganov 2024-01-12 14:02:30 +02:00
  • fa5c1fb44a
    backend_sched : fix assignments slaren 2024-01-12 20:38:34 +01:00
  • 52ee4540c0
    examples : add pydantic models to GBNF grammar generator (#4883) Maximilian Winter 2024-01-12 20:46:45 +01:00
  • 3fe81781e3
    CUDA: faster q8_0 -> f16 dequantization (#4895) Johannes Gäßler 2024-01-12 20:38:54 +01:00
  • e7e4df031b
    llama : ggml-backend integration (#4766) slaren 2024-01-12 20:07:38 +01:00
  • 584d674be6
    llama : remove redundant assert for StableLM (#4901) Georgi Gerganov 2024-01-12 20:54:12 +02:00
  • 930f907d3e
    export-lora : use LLAMA_FILE_MAGIC_GGLA (#4894) Daniel Bevenius 2024-01-12 18:54:53 +01:00
  • e790eef21c
    llama.swiftui : update models layout (#4826) Zay 2024-01-12 05:48:00 -07:00
  • 5537d9d36b
    gitignore : imatrix Georgi Gerganov 2024-01-12 14:33:21 +02:00
  • 1b280c9fff
    CUDA: fix softmax compile for old CUDA versions (#4862) Johannes Gäßler 2024-01-12 12:30:41 +01:00
  • 3cabe80630
    llama : fix typo "imp_embd" -> "inp_embd" Georgi Gerganov 2024-01-12 13:10:19 +02:00
  • 4315a94366
    common : streamline the formatting of help (#4890) howlger 2024-01-12 12:05:32 +01:00
  • 2d00741e12
    py : fix lint (#4889) Georgi Gerganov 2024-01-12 13:03:38 +02:00
  • f445c0e68c
    llama : fix llm_build_k_shift to use correct n_rot (#4889) Georgi Gerganov 2024-01-12 13:01:56 +02:00
  • 326b418b59
    Importance Matrix calculation (#4861) Kawrakow 2024-01-12 06:59:57 +01:00
  • 1d118386fe
    server : fix infill when prompt is empty (#4833) Georgi Gerganov 2024-01-11 23:23:49 +02:00
  • 7edefbd79c
    main : better name for variable n_print (#4874) Georgi Gerganov 2024-01-11 22:46:26 +02:00
  • 3ca63b4538
    main : disable token count by default (#4874) Georgi Gerganov 2024-01-11 22:43:05 +02:00
  • b037787548
    swift : track ggml release branch (#4867) Georgi Gerganov 2024-01-11 21:58:28 +02:00
  • 469e75d0a3
    llama : restore intended k-quants mixes for MoE models (#4872) Kawrakow 2024-01-11 20:43:15 +01:00
  • 49662cbed3
    ggml : SOTA 2-bit quants (add IQ2_XS) (#4856) Kawrakow 2024-01-11 20:39:39 +01:00
  • 3ba5b8ca8e
    swift : pin ggml commit + remove ggml.h from spm-headers (#4878) Georgi Gerganov 2024-01-11 21:31:31 +02:00
  • 4330bd83fe
    server : implement credentialed CORS (#4514) Laura 2024-01-11 19:02:48 +01:00
  • 27379455c3
    server : support for multiple api keys (#4864) Michael Coppola 2024-01-11 12:51:17 -05:00
  • eab6795006
    server : add LOG_INFO when model is successfully loaded (#4881) Behnam M 2024-01-11 12:41:39 -05:00
  • d8d90aa343
    ci: nix-flake-update: new token with pr permissions (#4879) Someone 2024-01-11 17:22:34 +00:00
  • 43f76bf1c3
    main : print total token count and tokens consumed so far (#4874) pudepiedj 2024-01-11 16:14:52 +00:00
  • 2f043328e3
    server : fix typo in model name (#4876) Isaac McFadyen 2024-01-11 09:33:26 -05:00
  • 2a7c94db5f
    metal : put encoder debug group behind a define (#4873) Paul Tsochantaris 2024-01-11 14:31:52 +00:00
  • 64802ec00d
    sync : ggml Georgi Gerganov 2024-01-11 09:39:08 +02:00
  • 3267c2abc7
    metal : fix deprecation warning (ggml/690) Georgi Gerganov 2024-01-11 09:34:59 +02:00
  • f85a973aa1
    ggml : remove ggml_cpy_inplace and ggml_cont_inplace (ggml/693) Timothy Cronin 2024-01-11 02:27:48 -05:00
  • 5362e43962
    metal : wrap each operation in debug group (ggml/690) Jack Mousseau 2024-01-10 06:19:19 -08:00
  • e739de7909
    ggml : change GGML_MAX_NAME at compile time (ggml/682) leejet 2024-01-10 21:13:42 +08:00
  • c910e3c28a
    Fix execlp call (ggml/689) Halalaluyafail3 2024-01-09 11:16:37 -05:00
  • f34432ca1e
    fix : cuda order of synchronization when setting a buffer (ggml/679) Erik Scholz 2024-01-05 16:00:00 +01:00
  • 7a9f75c38b
    server : update readme to document the new /health endpoint (#4866) Behnam M 2024-01-11 02:12:05 -05:00
  • 5c1980d8d4
    server : fix build + rename enums (#4870) Georgi Gerganov 2024-01-11 09:10:34 +02:00
  • cd108e641d
    server : add a /health endpoint (#4860) Behnam M 2024-01-10 14:56:05 -05:00
  • 57d016ba2d
    llama : add additional suffixes for model params (#4834) Brian 2024-01-11 01:09:53 +11:00
  • 329ff61569
    llama : recognize 1B phi models (#4847) Austin 2024-01-10 08:39:09 -05:00
  • d34633d8db
    clip : support more quantization types (#4846) John 2024-01-10 14:37:09 +01:00
  • 4f56458d34
    Python script to compare commits with llama-bench (#4844) Johannes Gäßler 2024-01-10 01:04:33 +01:00
  • 6efb8eb30e
    convert.py : fix vanilla LLaMA model conversion (#4818) Austin 2024-01-09 13:46:46 -05:00
  • 36e5a08b20
    llava-cli : don't crash if --image flag is invalid (#4835) Justine Tunney 2024-01-09 09:59:14 -08:00
  • 4dccb38d9a
    metal : improve dequantize precision to match CPU (#4836) Georgi Gerganov 2024-01-09 19:37:08 +02:00
  • 9a818f7c42
    scripts : improve get-pg.sh (#4838) Georgi Gerganov 2024-01-09 19:20:45 +02:00
  • 18adb4e9bb
    readme : add 3rd party collama reference to UI list (#4840) iohub 2024-01-10 00:45:54 +08:00
  • d9653894df
    scripts : script to get Paul Graham essays in txt format (#4838) Georgi Gerganov 2024-01-09 16:23:05 +02:00
  • 128de3585b
    server : update readme about token probs (#4777) Behnam M 2024-01-09 05:02:05 -05:00
  • 8c58330318
    server : add api-key flag to documentation (#4832) Zsapi 2024-01-09 10:12:43 +01:00
  • 18c2e1752c
    ggml : fix vld1q_s8_x4 32-bit compat (#4828) Georgi Gerganov 2024-01-09 10:42:06 +02:00
  • 8f900abfc0
    CUDA: faster softmax via shared memory + fp16 math (#4742) Johannes Gäßler 2024-01-09 08:58:55 +01:00
  • 1fc2f265ff
    common : fix the short form of --grp-attn-w, not -gat (#4825) howlger 2024-01-08 20:05:53 +01:00