]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2024-07-18 65acmake : install all ggml public headers (#8480)
2024-07-18 Eric Zhangserver: use relative routes for static files in new...
2024-07-18 Brianconvert-*.py: GGUF Naming Convention Refactor and Metad...
2024-07-18 RunningLeonserver : respect `--special` cli arg (#8553)
2024-07-17 Johannes Gäßlerlookup: fibonacci hashing, fix crashes (#8548)
2024-07-17 Al Mochkinbuild : Fix docker build warnings (#8535) (#8537)
2024-07-17 BrianCONTRIBUTING.md : remove mention of noci (#8541)
2024-07-17 hipudding[CANN] Add Ascend NPU backend (#6035)
2024-07-17 Masaya, Katobatched: fix n_predict parameter (#8527)
2024-07-17 Georgi Gerganovllama : disable context-shift for DeepSeek v2 (#8501)
2024-07-16 Johannes Gäßlermake/cmake: add missing force MMQ/cuBLAS for HIP (...
2024-07-16 Briangguf-hash : update clib.json to point to original xxhas...
2024-07-16 Steve Bondsexport-lora : handle help argument (#8497)
2024-07-16 Georgi Gerganovllama : valign + remove unused ftype (#8502)
2024-07-16 compiladeconvert_hf : faster lazy safetensors (#8482)
2024-07-15 Xuan Son NguyenRefactor lora adapter support (#8332)
2024-07-15 Xuan Son Nguyenfix ci (#8494)
2024-07-15 Daniel Beveniusggml : suppress unknown pragma 'GCC' on windows (#8460)
2024-07-15 M-Aserver: update README.md with llama-server --help outpu...
2024-07-15 Georgi Gerganovcommon : add --no-cont-batching arg (#6358)
2024-07-15 NikolaiLyssogordocs: fix links in development docs [no ci] (#8481)
2024-07-15 Meng, Hengyu[SYCL] add concat through dim 1/2 (#8483)
2024-07-15 Georgi Gerganovllama : de-duplicate deepseek2 norm
2024-07-15 0cc4mVulkan MMQ Fix (#8479)
2024-07-14 compiladepydantic : replace uses of __annotations__ with get_typ...
2024-07-14 Georgi Gerganovflake.lock: Update (#8475)
2024-07-14 Georgi Gerganovllama : fix Gemma-2 Query scaling factors (#8473)
2024-07-14 Briangguf_hash.py: Add sha256 (#8470)
2024-07-14 compiladellama : fix pre-tokenization of non-special added token...
2024-07-13 bandotivulkan : cmake integration (#8119)
2024-07-13 Georgi Gerganovmetal : template-ify some of the kernels (#8447)
2024-07-12 Georgi Gerganovserver : handle content array in chat API (#8449)
2024-07-12 Georgi Gerganovmain : print error on empty input (#8456)
2024-07-12 Daniel Beveniusllama : suppress unary minus operator warning (#8448)
2024-07-12 Douglas Hanleyserver : ensure batches are either all embed or all...
2024-07-12 Armen Kaleshiandocker : fix filename for convert-hf-to-gguf.py in...
2024-07-12 Jiří Podivínconvert : remove fsep token from GPTRefactForCausalLM...
2024-07-12 Georgi Gerganovexamples : sprintf -> snprintf (#8434)
2024-07-12 Georgi Gerganovggml : minor naming changes (#8433)
2024-07-12 Chen Xi[SYCL] fix the mul_mat_id ut issues (#8427)
2024-07-11 Nicholai Tukanovggml : add NVPL BLAS support (#8329) (#8425)
2024-07-11 Daniel Beveniuscuda : suppress 'noreturn' warn in no_device_code ...
2024-07-11 Johannes GäßlerCUDA: optimize and refactor MMQ (#8416)
2024-07-11 Georgi Gerganovgitignore : deprecated binaries
2024-07-11 compiladetokenize : add --no-parse-special option (#8423)
2024-07-11 Georgi Gerganovllama : use F32 precision in Qwen2 attention and no...
2024-07-11 Clint HerronInitialize default slot sampling parameters from the...
2024-07-10 Clint HerronName Migration: Build the deprecation-warning 'main...
2024-07-10 AidanBeltonS[SYCL] Use multi_ptr to clean up deprecated warnings...
2024-07-10 Georgi Gerganovggml : move sgemm sources to llamafile subfolder (...
2024-07-10 Dibakar Gopeggml : add AArch64 optimized GEMV and GEMM Q4 kernels...
2024-07-10 M. Yusuf Sarıgözgguf-py rel pipeline (#8410)
2024-07-10 Borislav Stanimirovllama : C++20 compatibility for u8 strings (#8408)
2024-07-10 Borislav Stanimirovmsvc : silence codecvt c++17 deprecation warnings ...
2024-07-10 fairydreamingllama : add assert about missing llama_encode() call...
2024-07-10 RunningLeonpy : fix converter for internlm2 (#8321)
2024-07-10 laikpy : fix extra space in convert_hf_to_gguf.py (#8407)
2024-07-09 Clint HerronServer: Enable setting default sampling parameters...
2024-07-09 Andy SalernoUpdate README.md to fix broken link to docs (#8399)
2024-07-09 Clint HerronDeprecation warning to assist with migration to new...
2024-07-09 Johannes Gäßlermake/cmake: LLAMA_NO_CCACHE -> GGML_NO_CCACHE (#8392)
2024-07-09 Alberto Cabrera... sycl : Reenabled mmvq path for the SYCL Nvidia Backend...
2024-07-09 Borislav Stanimirovcmake : allow external ggml (#8370)
2024-07-09 daghanerdonmezreadme : fix typo [no ci] (#8389)
2024-07-09 compiladegguf-py : do not use internal numpy types (#7472)
2024-07-08 Georgi Gerganovflake.lock: Update (#8342)
2024-07-08 Alberto Cabrera... labeler : updated sycl to match docs and code refactor...
2024-07-08 b4b4oreadme : fix web link error [no ci] (#8347)
2024-07-08 Alberto Cabrera... sycl : fix powf call in device code (#8368)
2024-07-08 Georgi Gerganovscripts : fix sync for sycl
2024-07-08 Georgi Gerganovsync : ggml
2024-07-08 Georgi Gerganovtests : fix whitespace (#0)
2024-07-08 John Balisfeat: cuda implementation for `ggml_conv_transpose_1d...
2024-07-08 Kevin Wangcommon : preallocate sampling token data vector (#8363)
2024-07-08 Georgi Gerganovinfill : assert prefix/suffix tokens + remove old space...
2024-07-08 Kevin Wangcommon : avoid unnecessary logits fetch (#8358)
2024-07-08 toyerreadme : add supported glm models (#8360)
2024-07-07 compiladepy : type-check all Python scripts with Pyright (#8341)
2024-07-07 Denis SpasyukUpdate llama-cli documentation (#8315)
2024-07-07 Alex Tuddenhamci : add checks for cmake,make and ctest in ci/run...
2024-07-07 Andy Taireadme : update bindings list (#8222)
2024-07-07 Briangguf-hash: model wide and per tensor hashing using...
2024-07-07 toyerllama : support glm3 and glm4 (#8031)
2024-07-07 Georgi Gerganovllama : fix n_rot default (#8348)
2024-07-07 compiladepy : use cpu-only torch in requirements.txt (#8335)
2024-07-07 standby24x7finetune: Rename command name in README.md (#8343)
2024-07-07 standby24x7finetune: Rename an old command name in finetune.sh...
2024-07-07 Bjarke Viksøeserver: Retrieve prompt template in /props (#8337)
2024-07-06 Derrick T.... added support for Authorization Bearer tokens when...
2024-07-06 Xuan Son Nguyenupdate main readme (#8333)
2024-07-06 Daniel Beveniusllama : add early return for empty range (#8327)
2024-07-05 jaime-m-pDetokenizer fixes (#8039)
2024-07-05 Xuan Son NguyenReorganize documentation pages (#8325)
2024-07-05 Georgi Gerganovllama : fix compile warning (#8304)
2024-07-05 Natsucmake : add GGML_BUILD and GGML_SHARED macro definition...
2024-07-05 Ouadie EL FAROUKIEnabled more data types for oneMKL gemm_batch (#8236)
2024-07-05 Georgi Gerganovconvert : remove AWQ remnants (#8320)
2024-07-05 Georgi Gerganovllama : minor indentation during tensor loading (#8304)
2024-07-05 Johannes GäßlerCUDA: MMQ support for iq4_nl, iq4_xs (#8278)
2024-07-05 DanieleCUDA: revert part of the RDNA1 optimizations (#8309)
next