]> git.djapps.eu Git - pkg/ggml/sources/ggml/shortlog
pkg/ggml/sources/ggml
2023-12-27 WillCorticesAIUpdate comment for AdamW implementation reference....
2023-12-27 FantasyGmmFix new CUDA10 compilation errors (llama/4635)
2023-12-27 Georgi Gerganovsync : llama.cpp
2023-12-27 Georgi Gerganovcmake : update CUDA build to support VMM
2023-12-27 slarencuda : improve cuda pool efficiency using virtual memor...
2023-12-27 slarenfallback to CPU buffer if host buffer alloc fails ...
2023-12-27 Johannes GäßlerCUDA: fixed row rounding for 0 tensor splits (llama...
2023-12-27 Georgi Gerganovscripts : fix PR number parsing during sync
2023-12-24 Georgi Gerganovscripts : improve llama sync patch
2023-12-23 Georgi Gerganovscripts : sync tests / headers
2023-12-23 Georgi Gerganovscripts : remove exit
2023-12-23 Georgi Gerganovscripts : fix PR number sed
2023-12-23 Georgi Gerganovscripts : add sync-llama-am.sh
2023-12-22 Georgi Gerganovsync : llama.cpp (ggml_scale, ggml_row_size, ggml_mul_m...
2023-12-18 slarencuda : fix synchronization with tensor get/set (#659)
2023-12-18 leejetcuda : fix im2col_f32_f16 (#658)
2023-12-14 chengchicmake : change installation path of static libraries...
2023-12-13 Georgi Gerganovsync : llama (mul_mat_id + get_rows kernels, typos...
2023-12-13 Steward Garciaggml: new gpu kernels + extends ggml_leaky_relu + ggml_...
2023-12-13 ariez-xyzgguf : document Mixtral changes in spec (#646)
2023-12-08 Georgi Gerganovsync : whisper.cpp (metal soft max fix + example prints)
2023-12-07 Georgi Gerganovsync : llama.cpp (fused soft max, gpu cpy ops, etc...
2023-12-07 slarenggml-backend : remove backend self-registration (#641)
2023-12-07 slarentest-backend-ops : add performance eval mode + improve...
2023-12-05 slarentest-backend-ops : initialize ggml_argsort test with...
2023-12-05 Georgi Gerganovmetal : check supported ops at runtime (#632)
2023-12-05 slarenggml : full broadcast in mul, add, div + ggml_mul_mat_i...
2023-12-05 Georgi Gerganovreadme : add link to seamless_comm repo
2023-12-05 Juddggml : disable `fprintf` when building with NDEBUG...
2023-12-01 slarenggml-cuda : fix usage without CUDA devices (#627)
2023-12-01 RiverZhoucmake : add ROCm config (#626)
2023-11-30 slarenggml-backend update: buffer types, backend registry...
2023-11-23 magicsetests : update test-vec0.c for mingw (#619)
2023-11-23 Georgi Gerganovreadme : add vit.cpp (#618)
2023-11-19 slarengguf : add tokenizer.chat_template documentation (...
2023-11-17 Guillaume Wenzekggml : fix ggml_set_2d_inplace (#611)
2023-11-17 Georgi Gerganovgguf : prevent out-of-bounds-access on invalid magic...
2023-11-17 Georgi Gerganovsync : whisper.cpp (update whisper example + minor...
2023-11-16 Georgi Gerganovsync : llama.cpp (cuda, gguf and linker fixes)
2023-11-13 slarenupdate examples and tests to use ggml_allocr_new_measur...
2023-11-13 Georgi Gerganovsync : llama.cpp (CUDA ReLU, CPU-only with CUDA, bloom...
2023-11-12 Georgi Gerganovsync : whisper.cpp (whisper full GPU, fix warnings...
2023-11-12 Steward Garciaggml : replace conv 1D - 2D stage_0 and stage_1 with...
2023-11-03 Georgi Gerganovsync : whisper.cpp (ARM 32-bit, abort callback, wav_wri...
2023-11-03 Georgi Gerganovsync : llama.cpp (CUDA opts, ggml-quants, YARN, etc...
2023-11-02 Jiří Podivínsam : passing parameters and simple prompt (#598)
2023-11-02 Jiří Podivínsam : update documentation to provide executable exampl...
2023-11-01 Philpaxgguf : add file format specification (#302)
2023-11-01 Andreiggml-backend : use __declspec with msvc (#599)
2023-10-30 slarenggml-backend v2 : add ggml_backend_sched (#586)
2023-10-30 Radoslav Gerganovyolo : add example implementing YOLO object detection...
2023-10-30 Jiří Podivíngitignore : add ggml-model-f16.bin (#597)
2023-10-30 Borislav Stanimirovcmake : cuda architectures: allow user override, only...
2023-10-24 Georgi Gerganovsync : llama.cpp (CUDA, Metal, OpenCL, gguf magic,...
2023-10-24 PABggml : memset dst to 0 in `ggml_conv_transpose_1d`...
2023-10-20 Georgi Gerganovgpt-2 : fix allocr worst-case when n_parallel > prompt...
2023-10-20 Georgi Gerganovgpt-2 : add ignore-eos flag
2023-10-20 Georgi Gerganovgpt-2 : allow setting custom context size (i.e. large...
2023-10-16 Georgi Gerganovci : add SAM test + improve whisper test (#583)
2023-10-15 PABtests : add ggml_conv_transpose_1d test (#582)
2023-10-12 Georgi Gerganovci : add gpt-2-batched test
2023-10-12 Yavor Ivanovgpt-2 : add batched decoding example (#572)
2023-10-12 Georgi Gerganovci : add M1 node (#577)
2023-10-12 Shijiereadme : add qwen example (#575)
2023-10-11 Georgi Gerganovcmake : fix string matching
2023-10-11 slarentests : do not build test-vec1 on systems without avx...
2023-10-09 leejetggml : faster ggml_conv_2d using 2-stage op (#483)
2023-10-09 Borislav Stanimirovcuda : int counters for device, fix fprintf warning...
2023-10-09 Yavor IvanovDisable ggml-alloc assert for CPU version of Sam.cpp...
2023-10-08 Georgi Gerganovsync : llama.cpp (Metal + OpenCL + minor alibi) (#558)
2023-10-08 slarenfix MSVC build issues (#557)
2023-10-07 slarenggml-alloc : fix crash when used without ggml-backend...
2023-10-07 Pierre Alexandre... readme : mention Metal could be used for gpt-2 (#553)
2023-10-06 slarenggml backends interface v1 (#547)
2023-10-06 Hyunsung Leeggml : delete duplicate logging macros (#531)
2023-10-04 Georgi Gerganovsync : llama.cpp (training, refactoring) (#548)
2023-10-04 布客飞龙cmake : add OPENCL_LIB to solve problem [cannot resolve...
2023-09-28 skirodevggml : fix batch for ggml_conv_2d (#528)
2023-09-28 PABggml : add `GGML_OP_CONV_TRANSPOSE_1D` (#524)
2023-09-28 PABggml : complete implementation of `GGML_OP_CONV_1D...
2023-09-15 Georgi Gerganovci : add whisper test (#525)
2023-09-15 Georgi Gerganovexamples : fix compile warnings
2023-09-15 Georgi Gerganovsync : whisper.cpp (Metal + ggml sched_yield fix +...
2023-09-08 Diogoci : add Metal build (#514)
2023-09-08 Diogoci : add CLBlast build (#513)
2023-09-08 Jiahao Licuda : suppress compiler warning of unused variables...
2023-09-08 布客飞龙cmake : solve prob "clblast.h not found" (#506)
2023-09-08 Cebtenzzreggml : mark ggml_format_name as a printf-like function...
2023-09-08 Cebtenzzreggml : gguf_context const-correctness (#509)
2023-09-08 Georgi Gerganovsync : whisper (POSIX) (#511)
2023-09-08 YavorGIvanovFix SAM example mask output with latest ggml
2023-09-05 Jiahao Licuda : support flattened GLM-style rope to reduce kerne...
2023-09-05 Georgi Gerganovwhisper : minor sync
2023-09-05 Yavor Ivanovsam : remove ggml_repeat and use inplace operation...
2023-09-05 Georgi Gerganovggml : sync llama.cpp (view_src + alloc improvements...
2023-09-05 Georgi Gerganovwhisper : sync (match OpenAI input, convert, new featur...
2023-09-02 Georgi Gerganovggml : fix L-BFGS linesearch loop (close #501)
2023-08-30 Radoslav Gerganovmnist : update the README (#498)
2023-08-29 Borislav Stanimirovbuild : fix msvc warnings (#496)
2023-08-29 CebtenzzreCUDA: fix build and enable warnings (#494)
next