]> git.djapps.eu Git - pkg/ggml/sources/ggml/shortlog
pkg/ggml/sources/ggml
2023-04-30 Georgi Gerganovggml, whisper : sync whisper.cpp (GGML_FTYPE + Q5 WASM...
2023-04-30 Georgi Gerganovggml : fix labels for GGML_OP_ALIBI
2023-04-29 Georgi Gerganovggml : fix 32-bit ARM NEON
2023-04-29 Georgi Gerganovggml : use vzip instead of vuzp for consistency
2023-04-29 Georgi Gerganovggml : fix SHARED build
2023-04-29 Georgi Gerganovggml : sync llama.cpp (less memory for mul_mat f16...
2023-04-29 Georgi Gerganovscripts : add sync-whisper.sh
2023-04-29 Georgi Gerganovcommon : forgot to remove Q4_3 references
2023-04-29 Georgi Gerganovggml : remove Q4_3
2023-04-28 Georgi Gerganovggml : ggml_alibi() fixes (#113)
2023-04-28 Dan Forbesggml : add ggml_alibi (positional embedding) (#113)
2023-04-28 Georgi Gerganovggml : sync llama.cpp (CLBlast)
2023-04-28 Georgi Gerganovgitignore : add python env folders
2023-04-28 Santtu Keskinenreadme : add bert.cpp link (#114)
2023-04-27 Georgi Gerganovstablelm : put warning about bug in the implementation
2023-04-27 Georgi Gerganovggml : sync llama.cpp (Q5_0 + Q5_1) + refactor examples...
2023-04-24 Georgi Gerganovggml : sync llama.cpp (fix GCC 8 build, close #99)
2023-04-23 Georgi Gerganovggml : indentation
2023-04-23 Georgi Gerganovggml : add GGML_API for exporting shared symbols
2023-04-23 Georgi Gerganovggml : better PERF prints
2023-04-23 le.changtests : fix compile error (#98)
2023-04-23 appvoidgpt-2 : remove GPT-J unnecessary import (#91)
2023-04-23 AsukaMinatotests : remove type cast (#100)
2023-04-23 Georgi Gerganovggml : sync llama.cpp (AVX improvements)
2023-04-22 Georgi Gerganovggml : fix Q4_3 cuBLAS + fix quantize_row_q4_2()
2023-04-22 Georgi Gerganovexamples : refactor quantization tools
2023-04-22 Georgi Gerganovexamples : utils -> common
2023-04-22 Georgi Gerganovggml : fix ARM build
2023-04-22 Georgi Gerganovcmake : add CMake support for cuBLAS (#101)
2023-04-22 Georgi Gerganovexamples : add Q4_2 and Q4_3 quantization support
2023-04-22 Georgi Gerganovggml : sync llama.cpp (Q4_3 + CUDA)
2023-04-20 Bart Pellemnist : add missing header (#95)
2023-04-20 Georgi Gerganovstablelm : update README.md
2023-04-20 Georgi Gerganovminor : fix GPT-NeoX name
2023-04-20 Georgi Gerganovreadme : add StableLM reference
2023-04-20 Georgi Gerganovexamples : add StableLM example (#96)
2023-04-20 Georgi Gerganovggml : sync llama.cpp (cuBLAS, Q4_3, bug fix, etc)
2023-04-19 Georgi Gerganovggml : sync llama.cpp
2023-04-15 Georgi Gerganovexamples : update huggingface links
2023-04-15 Georgi Gerganovggml : sync llama.cpp
2023-04-15 Georgi Gerganovggml : add ggml_type_name()
2023-04-15 Georgi Gerganovggml : use posix_memalign on non-Windows env
2023-04-14 Georgi Gerganovggml : add unary and binary map operations
2023-04-14 Georgi Gerganovggml : avoid powf() calls in ggml_rope()
2023-04-14 Georgi Gerganovggml : fix ARM NEON dot product types
2023-04-13 Georgi Gerganovmnist : update README
2023-04-13 Georgi Gerganovmnist : minor fixes and adjustments
2023-04-13 Ray Cromwellexamples : MNIST example for ggml (#84)
2023-04-13 Georgi Gerganovggml : sync latest changes from llama.cpp
2023-04-13 Jakob Frickgpt-2 : typo fix for the Cerebras instructions (#57)
2023-04-13 Georgi Gerganovggml : add GGML_DEFAULT_N_THREADS
2023-04-13 LostRuinsgpt : fix pytorch converter text encodings (#78)
2023-04-12 Georgi Gerganovreadme : update roadmap
2023-04-11 Georgi Gerganovgpt-j : update inference to match latest llama.cpp...
2023-04-10 Georgi Gerganovggml : fix <windows.h> include
2023-04-10 Georgi Gerganovggml : fix WASM build
2023-04-10 Georgi Gerganovwhisper : sync with whisper.cpp
2023-04-10 Georgi Gerganovggml : optimize ggml_cpy() for contiguous dst
2023-04-10 Georgi Gerganovggml : sync with llama.cpp
2023-04-10 LostRuinsgpt : initialize f16 tables during quantization (#77)
2023-04-07 Georgi Gerganovreadme : update Roadmap (add rwkv.cpp)
2023-03-30 Georgi Gerganovgpt-2 : minor update readme
2023-03-30 Georgi Gerganovgpt-2 : fix qunatize tool to quantize the "lm_head...
2023-03-30 Georgi Gerganovgpt-2 : add Cerebras-GPT example
2023-03-30 Supreet Sethiggml : fix NEON sign types (#51)
2023-03-29 Cordeirogpt-2 : convert h5 to ggml (#35)
2023-03-29 Georgi Gerganovreadme : update Roadmap
2023-03-29 Georgi Gerganovggml : 4-bit Integer quantisation + many llama.cpp...
2023-03-25 MaiHDggml : make it work on Windows (#46)
2023-03-25 Georgi Gerganovtests : add test-blas0
2023-03-22 Georgi GerganovFix CMake indentation
2023-03-22 katsu560add OpenBLAS detection and modify tests codes (#40)
2023-03-22 Alex von Gluck IVCMakeLists: Fix Haiku CPU detection (#39)
2023-03-22 hidenorlyAdd pipe input for prompt on gpt examples (#38)
2023-03-06 katsu560cmake : update CMakeLists.txt to add correct flags...
2023-03-06 Georgi Gerganovreadme : update Roadmap
2023-03-05 Georgi Gerganovreadme : add Roadmap section
2023-02-26 Georgi Gerganovsync : latest whisper.cpp
2023-02-21 Georgi Gerganovtests : fix cblas_sgemm call
2023-02-18 Georgi Gerganovtests : add SVD experiments
2023-02-15 Georgi Gerganovsync : latest whisper.cpp (scratch buffers in ggml)
2023-01-20 Georgi GerganovUpdate README.md
2023-01-15 Takuya Takeuchicmake : configure CMAKE_C_FLAGS and target_link_librari...
2023-01-15 Georgi Gerganovgpt : fix sampling to use the temperature (close #16)
2023-01-15 Georgi Gerganovggml : sync latest whisper.cpp
2023-01-08 Georgi Gerganovgpt-2 : fix broken prompt due to recent experiments
2023-01-08 Georgi Gerganovggml : sync latest whisper.cpp
2023-01-07 Georgi Gerganovcmake : disable warnings about unused functions
2023-01-07 Georgi Gerganovggml : bugfix in new soft max computation
2023-01-07 Georgi Gerganovtests : change test2 eps
2023-01-07 Georgi Gerganovggml : sync with latest whisper.cpp
2023-01-07 Georgi Gerganovtests : some more quantization experiments
2023-01-07 Georgi Gerganovsync : forgot to sync ggml.h
2023-01-07 Georgi Gerganovsync : latest changes from whisper.cpp
2023-01-07 Georgi Gerganovtests : wip quantized matrix multiplication method 2
2023-01-07 Georgi Gerganovtests : minor fixes for x86
2023-01-05 Georgi Gerganovtests : experiments with n-bit quantized matrix multipl...
2022-12-31 Georgi Gerganovsync : latest changes from whisper.cpp
2022-12-31 Georgi Gerganovgpt-2 : experimenting with attention mask
2022-12-31 Georgi Gerganovgpt-2 : fix off-by-one error in batching logic
next