]> git.djapps.eu Git - pkg/ggml/sources/ggml/shortlog
pkg/ggml/sources/ggml
2023-08-22 Jeffrey Quesnellecmake : fix MSVC building with CUDA (#424)
2023-08-22 leejetggml : sync new operators from stable-diffusion.cpp...
2023-08-22 Olivier ChafikMerge pull request #449 from ochafik/python-stubs
2023-08-22 Olivier Chafikpython: regenerate bindings + cosmetic cleanups
2023-08-22 Brad Itostarcoder : fix starcoder/convert-hf-to-ggml.py to...
2023-08-22 Jiahao Licuda : add alibi op (#457)
2023-08-22 Georgi Gerganovggml : rename xPos variables to unify coding style
2023-08-22 Jan Ploskiggml : implementation of xPos RoPE (#441); also extends...
2023-08-22 Georgi Gerganovggml : sync latest llama.cpp (GGUF) (#470)
2023-08-21 Yavor Ivanovggml : improve ADD_REL_POS perf in SAM by doing it...
2023-08-18 YavorGIvanovUpdate README to point to SAM example
2023-08-18 Georgi Gerganovexamples : add sample SAM inference (#74)
2023-08-16 Metal Whalezig : update `build.zig` file to make it work with...
2023-08-16 klosaxexamples : fix tensor name access (#443)
2023-08-16 Sam Spilsburyggml : backport ggml-alloc from llama.cpp (#433)
2023-08-14 ochafikAdded some tests to python example + fixed numpy on...
2023-08-13 ochafikSimple python stub (*.pyi) generator for cffi
2023-08-13 ochafikAdd python example w/ cffi-generated bindings
2023-08-13 leejetreadme : add stable-diffusion example (#447)
2023-08-07 Georgi Gerganovggml : mul mat tweaks (#439)
2023-08-07 Georgi Gerganovggml : pad result of ggml_nbytes()
2023-08-07 Georgi Gerganovggml : sync llama.cpp (memory allocator + cuda + metal)
2023-08-06 Jiahao Licmake : add avx compile options on Windows (synced...
2023-08-03 Borislav Stanimirovcmake : fix msvc cuda build - no need to specify stdlib...
2023-08-03 Borislav Stanimirovtests : fixed windows build (#426)
2023-08-01 slarenMerge pull request #422 from ggerganov/ggml-map-custom-new
2023-07-31 slarentest-customop.c : more comments
2023-07-31 slarenfix formatting
2023-07-30 slarenggml : add ggml_map_custom1-3
2023-07-26 johnson442starcoder : fix unused variable warnings (#416)
2023-07-25 Georgi Gerganovggml : sync llama.cpp (#415)
2023-07-25 klosaxreadme : add chatglm example (#414)
2023-07-24 Georgi Gerganovtests : remove unnecessary funcs
2023-07-24 Borislav Stanimirovstarcoder : fix windows build, fix cast warnings (...
2023-07-23 Andreicmake : add metal kernel to target resources when built...
2023-07-23 Ivan Zdaneggml : refactor unary ops (#405)
2023-07-23 goerchggml : add coverage measurement for Clang, increase...
2023-07-23 Jiahao Liggml : add get_no_alloc api corresponding to set_no_all...
2023-07-23 Cebtenzzreggml : build with -Wmissing-prototypes, fix warnings...
2023-07-23 Reza Rezvancommon : fix param parsing (#391)
2023-07-23 taherggml : add vector scaling using Accelerate (#380)
2023-07-23 Georgi Gerganovggml : sync llama.cpp (#409)
2023-07-23 Tom Baileyreadme : fix gpt-neox docs (#410)
2023-07-23 fitzsimcmake : add PPC64 support (#392)
2023-07-23 Jiahao Licmake : sync metal compile scripts from llama.cpp ...
2023-07-22 Georgi Gerganovreadme : add minigpt4 link
2023-07-22 Georgi Gerganovci : avoid hardcoded number of threads
2023-07-18 Georgi Gerganovci : update to be able to run locally
2023-07-18 Georgi Gerganovggml : sync llama.cpp (fix PERF + CUDA dup cont support)
2023-07-17 Georgi Gerganovci : disable wget progress
2023-07-17 Georgi Gerganovci : use models-mnt
2023-07-16 Georgi Gerganovci : integrate with ggml-org/ci (#393)
2023-07-15 Georgi Gerganovggml : sync llama.cpp (CUDA add/mul bcast + Metal fix...
2023-07-14 johnson442starcoder : mmap (and gpu) example (#338)
2023-07-14 Johannes Gäßlercuda : fix CUDA arch: OFF -> 52;61 (#389)
2023-07-14 Georgi Gerganovggml : sync llama.cpp (fix CUDA build, faster Metal)
2023-07-14 Jiahao Licuda : support GLM-style RoPE (#383)
2023-07-14 Georgi Gerganovggml : retire custom ggml_2d impl in favor of general...
2023-07-14 David Millerggml : general conv_2d CPU implementation (#352)
2023-07-14 Georgi Gerganovggml : fix mul_mat src1 indexing when not contiguous...
2023-07-14 Georgi Gerganovggml : fix mul_mat src1 indexing when src1 is not conti...
2023-07-12 Georgi Gerganovggml : apply mul_mat broadcast fix (sync llama.cpp)
2023-07-12 Georgi Gerganovcuda : sync llama.cpp
2023-07-12 M. Yusuf Sarıgözggml : broadcast mul_mat + conv batch support (#325)
2023-07-12 Georgi Gerganovggml : pool naming changes + coding style fixes
2023-07-12 Jiahao Liggml : add CUDA gelu op (#374)
2023-07-12 Borislav Stanimirovggml : basic implementation of 1d and 2d pools (#375)
2023-07-12 Georgi Gerganovggml : revert CUDA broadcasting changes until fixed
2023-07-11 Georgi Gerganovggml : remove unused function (#328)
2023-07-11 Georgi Gerganovggml : fix compile warnings after #328
2023-07-11 Arjunggml : add callback to abort ggml_graph_compute() ...
2023-07-11 Jiahao Liggml : use a single kernel for CUDA mul op (#373)
2023-07-11 Borislav Stanimirovtests : ifdef for #pragma GCC (#370)
2023-07-11 Georgi Gerganovreadme : add link to ggllm.cpp repo (close #361)
2023-07-11 Jiahao Liggml : broadcast ggml_add() for F32 (#359)
2023-07-11 Jiahao Liggml : support norm op on CUDA (#364)
2023-07-11 Tom Jobbinsstarcoder : fix for ggml-model.bin being saved in wrong...
2023-07-11 goerchggml : fix ggml_set_xxx (#354)
2023-07-11 Daulet Zhanguzinggml : fix Alibi implementation (#351)
2023-07-11 Georgi Gerganovggml : sync llama.cpp (fix for #341)
2023-07-10 Georgi Gerganovggml : fix docs about element access (close #348)
2023-07-10 the-crypt-keeperstarcoder : add <|end_of_turn|> token handling in order...
2023-07-10 Sam Spilsburypkg-config : fix typo in includedir (#367)
2023-07-10 Georgi Gerganovggml : sync llama.cpp (changes to ggml_graph_compute...
2023-07-06 Georgi Gerganovggml : minor indentation
2023-07-06 Borislav Stanimirovggml : restore GGML_RESTRICT (#350)
2023-07-05 Georgi Gerganovggml : fix bug introduced in bfc6d42f8c2141383e4f21e4a0...
2023-07-05 Georgi Gerganovtests : sync from llama.cpp and disable some obsolete...
2023-07-05 Georgi Gerganovggml : sync llama.cpp (generalize quantize_fns + CUDA...
2023-07-04 Andreicmake : fix public header path for submodules (#342)
2023-07-04 Georgi Gerganovwhisper : fix wrong variable name from previous commit
2023-07-04 Sam Spilsburybuild : add pkg-config file (#335)
2023-07-04 Sam Spilsburycmake : install the header file to ggml/ggml.h (#333)
2023-07-04 Georgi Gerganovwhisper : sync whisper.cpp (tinydiarize + OpenVINO)
2023-07-04 Sam Spilsburyreadme : add link to ggml-gobject (#336)
2023-07-04 Jakob Frickdolly : update error print behavior (#337)
2023-07-04 Borislav Stanimirovdolly : disable interactive_port on Windows (#339)
2023-07-02 Jakob Frickdolly : add interactive prompt and port mode (#319)
2023-07-02 Georgi Gerganovexamples : remove whitespace
2023-07-02 Hirochika Matsumotoexamples : use GGML_FILE_MAGIC where possible (#323)
next