]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2023-09-16 IsaacDynamoEnable BUILD_SHARED_LIBS=ON on all Windows builds ...
2023-09-16 VladEnable build with CUDA 11.0 (make) (#3132)
2023-09-16 goerchFixing the last deviations from sentencepiece indicated...
2023-09-15 Cebtenzzreexamples : add compiler version and target to build...
2023-09-15 Cebtenzzrecheck C++ code with -Wmissing-declarations (#3184)
2023-09-15 Cebtenzzrefix build numbers by setting fetch-depth=0 (#3197)
2023-09-15 Meng Zhangllama : add support for StarCoder model architectures...
2023-09-15 Cebtenzzrecommon : do not use GNU zero-length __VA_ARGS__ extensi...
2023-09-15 Georgi Gerganovmetal : fix bug in soft_max kernels (out-of-bounds...
2023-09-15 Cebtenzzreconvert : make ftype optional in simple scripts (#3185)
2023-09-15 Georgi Gerganovsync : ggml (Metal F32 support + reduce ggml-alloc...
2023-09-15 Engininja2cmake : fix building shared libs for clang (rocm) on...
2023-09-15 Evgeny Kurnevskyflake : use pkg-config instead of pkgconfig (#3188)
2023-09-15 Georgi Gerganovmetal : relax conditions on fast matrix multiplication...
2023-09-15 Andreicmake : fix llama.h location when built outside of...
2023-09-15 Ali Tariqci : Cloud-V for RISC-V builds (#3160)
2023-09-15 Rolandllama : remove mtest (#3177)
2023-09-15 Cebtenzzrellama : make quantize example up to 2.7x faster (#3115)
2023-09-14 jneemflake : allow $out/include to already exist (#3175)
2023-09-14 Andreicmake : compile ggml-rocm with -fpic when building...
2023-09-14 Asbjørn Ollingflake : include llama.h in nix output (#3159)
2023-09-14 Cebtenzzremake : fix clang++ detection, move some definitions...
2023-09-14 AlonCI: add FreeBSD & simplify CUDA windows (#3053)
2023-09-14 akawrykowfalcon : use stated vocab size (#2914)
2023-09-14 bandoticmake : add relocatable Llama package (#2960)
2023-09-14 dylandocker : add gpu image CI builds (#3103)
2023-09-14 Kerfufflegguf-py : support identity operation in TensorNameMap...
2023-09-14 jameswu2014feature : support Baichuan serial models (#3009)
2023-09-14 Leng Yuespeculative : add heuristic algorithm (#3006)
2023-09-13 goerchwhisper : tokenizer fix + re-enable tokenizer test...
2023-09-13 Tristan Rosscmake : add a compiler flag check for FP16 format ...
2023-09-13 Johannes GäßlerCUDA: mul_mat_q RDNA2 tunings (#2910)
2023-09-13 FKspeculative: add --n-gpu-layers-draft option (#3063)
2023-09-13 Eric Sommerladearm64 support for windows (#3007)
2023-09-12 Johannes GäßlerCUDA: fix LoRAs (#3130)
2023-09-11 Johannes GäßlerCUDA: fix mul_mat_q not used for output tensor (#3127)
2023-09-11 Johannes GäßlerCUDA: lower GPU latency + fix Windows performance ...
2023-09-11 Jhen-Jie Hongcmake : support build for iOS/tvOS (#3116)
2023-09-11 Johannes GäßlerCUDA: add device number to error messages (#3112)
2023-09-11 Kawrakowmetal : PP speedup (#3084)
2023-09-10 Erik Scholzconvert: remove most of the n_mult usage in convert...
2023-09-09 kchro3metal : support for Swift (#3078)
2023-09-09 Jhen-Jie Hongmetal : support build for iOS/tvOS (#3089)
2023-09-08 takov751flake : add train-text-from-scratch to flake.nix (...
2023-09-08 Ikko Eltociear... readme : fix typo (#3043)
2023-09-08 Kawrakowmetal : Q3_K speedup (#2995)
2023-09-08 Cebtenzzreexamples : make n_ctx warning work again (#3066)
2023-09-08 Georgi Gerganovreadme : update hot tpoics
2023-09-08 Georgi Gerganovsync : ggml (CUDA GLM RoPE + POSIX) (#3082)
2023-09-08 Przemysław... build : do not use _GNU_SOURCE gratuitously (#2035)
2023-09-08 hongbo.modocker : add git to full-cuda.Dockerfile main-cuda...
2023-09-08 YuiUpdate deprecated GGML TheBloke links to GGUF (#3079)
2023-09-08 slarenggml-alloc : correctly check mmap return value for...
2023-09-08 Kunshang Jienable CPU HBM (#2603)
2023-09-07 Cebtenzzreconvert : fix F32 ftype not being saved (#3048)
2023-09-07 Cebtenzzrefix some warnings from gcc and clang-tidy (#3038)
2023-09-07 Cebtenzzremake : improve test target (#3031)
2023-09-07 Cebtenzzremake : fix CPPFLAGS (#3035)
2023-09-07 slarenllama-bench : use two tokens in the warmup run for...
2023-09-07 Kawrakowmetal : parallel RoPE on Metal (#3024)
2023-09-07 Kawrakowmetal : correct fix of kernel_norm (#3060)
2023-09-07 Georgi Gerganovmetal : fix kernel_norm (fixes Falcon on Metal) (#3057)
2023-09-07 Przemysław... ggml : posixify madvise and pagesize (#3037)
2023-09-06 Georgi Gerganovk-quants : fix zero-weight guard in Q6_K (ref #3040)
2023-09-06 Kerfuffleconvert-llama-ggml-to-gguf: Try to handle files older...
2023-09-05 Cebtenzzrebuild : add LLAMA_METAL_NDEBUG flag (#3033)
2023-09-05 Cebtenzzremake : use new flag variables for recent changes (...
2023-09-05 Cebtenzzreexamples : replace fprintf to stdout with printf (...
2023-09-05 Erik Scholzconvert: fix convert.py not working with int filename_s...
2023-09-05 KawrakowGuard against all weights in a super-block being zero...
2023-09-05 Georgi Gerganovllama : update logic for number of threads when using...
2023-09-05 Georgi Gerganovspeculative : add grammar support (#2991)
2023-09-04 Georgi Gerganovpy : minor
2023-09-04 Georgi Gerganovbuild : on Mac OS enable Metal by default (#2901)
2023-09-04 slarenggml-opencl : store GPU buffer in ggml_tensor::extra...
2023-09-04 Cebtenzzrellama-bench : make cpp file non-executable (#2999)
2023-09-04 Leng Yuemake : add speculative example (#3003)
2023-09-04 Aarni Koskelaserver : add a subtle loading animation to the edit...
2023-09-04 Jiahao Li2x faster (rms) norm cuda kernels (3.7% e2e improvement...
2023-09-03 slarenggml-alloc : use virtual memory for measurement (#2973)
2023-09-03 Georgi Gerganovspeculative : PoC for speeding-up inference via specula...
2023-09-03 Georgi Gerganovperplexity : fix ETA by warming up the model with an...
2023-09-03 Kerfufflegguf(python): Fix special vocab handling when id <...
2023-09-03 Georgi Gerganovmetal : restore 363f0bf and fix reduce in F16_F32 kerne...
2023-09-03 Aloncov : disable comment in PRs (#2989)
2023-09-03 opparcollama : fix bpe tokenize from byte (#2889)
2023-09-03 Georgi Gerganovmetal : revert 6af0bab until we fix it
2023-09-03 Aloncov : add Code Coverage and codecov.io integration...
2023-09-03 Wentai Zhangopencl : fix a bug in ggml_cl_pool_malloc() for ggml_cl...
2023-09-03 Kawrakowmetal : more optimizations (#2959)
2023-09-03 kchro3swift : add support for k-quants (#2983)
2023-09-03 Kerfuffleconvert.py : BPE fixes (#2938)
2023-09-03 Ido Sdocs : add `catai` to `README.md` (#2967)
2023-09-03 momongaexamples : fix gpt-neox (#2943)
2023-09-03 kchro3swift : add missing c file to Package.swift (#2978)
2023-09-03 Cebtenzzremake : support overriding CFLAGS/CXXFLAGS/CPPFLAGS...
2023-09-02 Kerfufflelogging: Fix creating empty file even when disabled...
2023-09-02 bandotireadme : update clblast instructions (#2903)
2023-09-02 Karsten Weissmetal : show all Metal device instances in the system...
2023-09-02 Jhen-Jie Hongk-quants : fix build on armv7 (android only) (#2920)
next