]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2023-11-27 Kasumireadme : add Amica to UI list (#4230)
2023-11-27 Bailey Chittleexamples : iOS example with swift ui (#4159)
2023-11-27 Jared Van Bortelggml : fix -Warray-bounds warning with gcc (#4231)
2023-11-26 Georgi Gerganovlookahead : support `-n -1` infinite generation
2023-11-26 Georgi Gerganovreadme : update hot topics
2023-11-26 Georgi Gerganovlookahead : add example for lookahead decoding (#4207)
2023-11-26 Xiao-Yong Jinmetal : fix yarn (#4220)
2023-11-25 Galunidscripts : Use mmap in torch load (#4202)
2023-11-25 Marcus Dunnllama : grammar `reserve` space in `decode_utf8` (...
2023-11-25 crasmUpdate docs for yarn_ext_factor <0.0 as unspecified...
2023-11-25 Georgi Gerganovreadme : update hot topics
2023-11-25 Georgi Gerganovserver : OAI API compatibility (#4198)
2023-11-24 slarenllama : set metal log callback correctly (#4204)
2023-11-24 slarenggml-cuda : support stablelm rope (#4156)
2023-11-24 Galunidconvert : fix tensors using grad in some models (#4173)
2023-11-24 eastrivermain.swift : fix eos checking (#4197)
2023-11-24 Aaryaman Vasishtareadme : use PATH for Windows ROCm (#4195)
2023-11-23 Haohui MaiFix incorrect format strings and uninitialized variable...
2023-11-23 Georgi Gerganovllama : KV cache view API + better KV cache management...
2023-11-23 Georgi Gerganovreadme : update hot topics
2023-11-23 Daniel Beveniusexamples : fix typo in parallel example doc comment...
2023-11-23 Georgi Gerganovdocs : add llama-star arch idea
2023-11-21 Galunidstablelm : simplify + speedup generation (#4153)
2023-11-20 Galunidfinetune - update readme to mention llama support only...
2023-11-20 Aaryaman Vasishtareadme : update ROCm Windows instructions (#4122)
2023-11-20 Seb Cmain : Add ChatML functionality to main example (#4046)
2023-11-20 Galunidci : add flake8 to github actions (python linting)...
2023-11-20 Branden Butlerspeculative : fix prompt tokenization in speculative...
2023-11-19 Georgi GerganovRevert "finetune : add --n-gpu-layers flag info to...
2023-11-19 Clark Sabenfinetune : add --n-gpu-layers flag info to --help ...
2023-11-19 SoftwareRendererserver : relay error messages (#4131)
2023-11-19 kchro3common : comma should be semicolon (#4137)
2023-11-19 Georgi Gerganovgitignore : tokenize
2023-11-19 slarengguf-py : export chat templates (#4125)
2023-11-18 Kerfuffletokenize example: Respect normal add BOS token behavior...
2023-11-18 Galunidscripts : Remove missed baichuan convert script (#4127)
2023-11-18 KerfuffleClean up ggml-cuda.cu warnings when compiling with...
2023-11-17 slarenllama : increase max nodes (#4115)
2023-11-17 Roger Meierbuild : support ppc64le build for make and CMake (...
2023-11-17 Georgi Gerganovtokenize : fix trailing whitespace
2023-11-17 zakkorexamples : add tokenize (#4039)
2023-11-17 Don Mahurinconvert : use 'model' value if it exists. This allows...
2023-11-17 Johnpy : Falcon HF compatibility (#4104)
2023-11-17 Jannis Schönlebercommon : improve yaml log escaping (#4080)
2023-11-17 Huawei Linllava : fix compilation warning that fread return value...
2023-11-17 Jiří Podivínpy : remove superfluous import statements (#4076)
2023-11-17 Jiří Podivíntrain : move number of gpu layers argument parsing...
2023-11-17 slarenllama : add functions to get the model's metadata ...
2023-11-17 gwjrfinetune : speed-up ggml_compute_forward_out_prod_f32...
2023-11-17 Andrew Godfreyfinetune : zero the loraB initial vectors (#4082)
2023-11-17 Andrew Godfreycuda : get_row_rounding F32 (#4095)
2023-11-17 Georgi Gerganovllama : fix data units (#4101)
2023-11-17 KerfuffleRespect tokenizer.ggml.add_bos_token value when tokeniz...
2023-11-16 texmex76gguf : fix potential infinite loops while parsing ...
2023-11-15 Jared Van Bortelllama : restore prefix space in llama tokenizer (#4081)
2023-11-15 slarenggml-cuda : increase max graph size (#4084)
2023-11-14 Michael PotterFix MacOS Sonoma model quantization (#4052)
2023-11-14 Galunidstablelm : StableLM support (#3586)
2023-11-14 afridevaconvert.py: also look for plain model.safetensors ...
2023-11-13 M. Yusuf Sarıgözllava : fix regression for square images in #3613 ...
2023-11-13 Georgi Gerganovggml : sync (im2col, GPU conv, 32-bit arm compat) ...
2023-11-13 Georgi Gerganovreadme : update hot topics
2023-11-13 Georgi Gerganovsync : ggml (backend v2) (#3912)
2023-11-13 KerfuffleAdd ReLU and SQR CUDA ops to (partially) fix Persimmon...
2023-11-12 Kerfufflegguf-py: gguf_writer: Use bytearray to build metadata...
2023-11-12 Richard KissFix some documentation typos/grammar mistakes (#4032)
2023-11-11 M. Yusuf SarıgözFix gguf-convert-endian script (#4037)
2023-11-11 Alexey Parfenovserver : fix crash when prompt exceeds context size...
2023-11-11 Kerfufflegguf-py: Refactor and allow reading/modifying existing...
2023-11-10 Jhen-Jie Hongserver : allow continue edit on completion mode (#3950)
2023-11-10 GalunidUnbreak persimmon after #3837 (#4010)
2023-11-09 Galunidscripts: Generalize convert scripts (#3838)
2023-11-09 Mihaiserver : add min_p param (#3877)
2023-11-08 slarenggml-alloc : fix backend assignments of views (#3982)
2023-11-07 Jared Van Bortelgguf : track writer state, free unneeded tensors, clean...
2023-11-07 Georgi Gerganovmake : do not add linker flags when compiling static...
2023-11-07 xaedesggml : fix backward rope after YaRN (#3974)
2023-11-07 Matthew TejoUse params when loading models in llava-cli (#3976)
2023-11-07 Meng Zhangcuda : supports running on CPU for GGML_USE_CUBLAS...
2023-11-06 Damian Stewartllava : expose as a shared library for downstream proje...
2023-11-05 slarenggml-cuda : fix f16 mul mat (#3961)
2023-11-05 KerfuffleAllow common process_escapes to handle \x sequences...
2023-11-05 Thái Hoàng Tâmserver : fix typo for --alias shortcut from -m to ...
2023-11-05 Jared Van Bortelcuda : fix disabling device with --tensor-split 1,0...
2023-11-05 Meng Zhangllama : mark LLM_ARCH_STARCODER as full offload support...
2023-11-05 Evecmake : MSVC instruction detection (fixed up #809)...
2023-11-05 Eveci : use intel sde when ci cpu doesn't support avx512...
2023-11-05 slarencuda : revert CUDA pool stuff (#3944)
2023-11-04 Kerfufflegguf-py: Support 01.AI Yi models (#3943)
2023-11-03 Peter Sugiharametal : round up to 16 to fix MTLDebugComputeCommandEnc...
2023-11-03 Xiao-Yong Jinggml-metal: fix yarn rope (#3937)
2023-11-03 slarenggml-cuda : move row numbers to x grid dim in mmv kerne...
2023-11-03 Georgi Gerganovspeculative : change default p_accept to 0.5 + CLI...
2023-11-03 Georgi Gerganovcommon : YAYF (yet another YARN fix) (#3925)
2023-11-03 cebtenzzrellama : change yarn_ext_factor placeholder to -1 (...
2023-11-02 Kerfufflecuda : add ROCM aliases for CUDA pool stuff (#3918)
2023-11-02 Andreicmake : fix relative path to git submodule index (...
2023-11-02 Georgi Gerganovreadme : add notice about #3912
2023-11-02 Georgi Gerganovcuda : fix const ptrs warning causing ROCm build issues...
2023-11-02 Oleksii Maryshchenkocuda : use CUDA memory pool with async memory allocatio...
next