]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/shortlog
pkg/ggml/sources/whisper.cpp
2024-10-16 toboil-featuresreadme : add Vulkan notice (#2488)
2024-10-16 Georgi Gerganovmake : fix GGML_VULKAN=1 build (#2485)
2024-10-15 Rotem Danwhisper : add dtw preset for large-v3-turbo (#2481)
2024-10-14 CrispStrobeconvert : handle max_target_positions (#2477)
2024-10-14 Salman Farozreadme : update the Quick Start section (#2475)
2024-10-08 Sandro Haneawhisper : add OpenVINO init with state (#2464)
2024-10-07 Georgi Gerganovrelease : v1.7.1
2024-10-06 SRHMorrisvulkan : retry allocation with fallback flags (#2451)
2024-10-05 Georgi Gerganovrelease : v1.7.0
2024-10-05 Georgi Gerganovscripts : bench v3-turbo
2024-10-05 Georgi Gerganovwhisper : remove mel leftover constants (396089f)
2024-10-05 Georgi Gerganovwhisper : zero-out the KV cache upon clear (#2445)
2024-10-05 Georgi Gerganovobjc : fix build
2024-10-05 Georgi Gerganovmetal : zero-init buffer contexts (#0)
2024-10-05 Georgi Gerganovwhisper : revert mel-related changes (#0)
2024-10-05 Georgi Gerganovwhisper : adapt to latest ggml (skip) (#0)
2024-10-05 Daniel Beveniusggml : fix typo in example usage ggml_gallocr_new ...
2024-10-05 Diego Devesaggml : fixes after sync (ggml/983)
2024-10-05 Diego Devesaggml-backend : add device and backend reg interfaces...
2024-10-05 Ouadie EL FAROUKIFixed dequant precision issues in Q4_1 and Q5_1 (llama...
2024-10-05 Diego Devesaggml-backend : add device and backend reg interfaces...
2024-10-05 Alberto Cabrera... Initial cmake support of SYCL for AMD GPUs (llama/9658)
2024-10-05 Radoslav Gerganovvulkan : do not use tensor->extra (llama/9407)
2024-10-05 Johannes Gäßlerggml/ex: calculate accuracy in graph, adapt MNIST ...
2024-10-05 Johannes Gäßlerggml: refactor cross entropy loss CPU impl. (ggml/976)
2024-10-05 Georgi Gerganovscripts : sync ggml-backend.cpp
2024-10-05 Georgi Gerganovwhisper : fix excessive memory usage (#2443)
2024-10-04 Rahul Vadhyarexamples : update dr_wav.h to newer version (#2449)
2024-10-03 Georgi Gerganovtalk-llama : sync llama.cpp
2024-10-03 Georgi Gerganovmetal : reduce command encoding overhead (llama/9698)
2024-10-03 Georgi Gerganovsync : ggml
2024-10-03 Johannes Gäßlertest: fix OPT_STEP_ADAMW for test-backend-ops (ggml...
2024-10-03 Salvatore Mesoracavulkan : mul_mat: fix UB with small warps (ggml/952)
2024-10-03 Borislav Stanimirovggml : fix ggml_cast (ggml/973)
2024-10-03 Johannes Gäßlerggml: fix gradient allocation logic (ggml/966)
2024-10-03 Georgi Gerganovggml : define missing HWCAP flags (llama/9684)
2024-10-03 Dan Johanssonggml : add run-time detection of neon, i8mm and sve...
2024-10-03 Markus TavenrathEnable use to the rebar feature to upload buffers to...
2024-10-03 R0CKSTARmtgpu: enable VMM (llama/9597)
2024-10-03 Charles Xuggml : remove assert for AArch64 GEMV and GEMM Q4 kerne...
2024-10-03 Dou Xinpengcann: fix crash when llama-bench is running on multiple...
2024-10-03 Johannes GäßlerCUDA: remove bad assert (ggml/972)
2024-10-03 Jeff Bolzvulkan : multithread pipeline creation (ggml/963)
2024-10-03 Jeff Bolzvulkan : fix build for GGML_VULKAN_RUN_TESTS, add TFLOP...
2024-10-03 Salvatore Mesoracavulkan : argsort barriers must be under uniform control...
2024-10-03 Georgi Gerganovggml : fix GGML_MAX_N_THREADS + improve formatting...
2024-10-02 gilbertgongserver : ffmpeg overwrite leftover temp file (#2431)
2024-10-01 Georgi Gerganovwhisper : add large-v3-turbo (#2440)
2024-09-27 Georgi Gerganovtests : remove test-backend-ops (#2434)
2024-09-25 Georgi Gerganovci : disable failing CUDA and Java builds
2024-09-24 Hugoreadme : fix references to download-ggml-model.sh ...
2024-09-24 Georgi Gerganovmake : remove "talk" target until updated
2024-09-24 Georgi Gerganovggml : add ggml-cpu-impl.h (skip) (#0)
2024-09-24 Georgi Gerganovsync : ggml
2024-09-24 Georgi Gerganovtalk-llama : sync llama.cpp
2024-09-24 Eric Zhangggml : add AVX512DQ requirement for AVX512 builds ...
2024-09-24 Georgi Gerganovlog : add CONT level for continuing previous log entry...
2024-09-24 Max Krasnyanskythreads: fix msvc build without openmp (llama/9615)
2024-09-24 Ivancuda: add q8_0->f32 cpy operation (llama/9571)
2024-09-24 Max Krasnyanskythreads: improve ggml_barrier scaling with large number...
2024-09-24 Srihari-mcwggml : AVX512 gemm for Q4_0_8_8 (llama/9532)
2024-09-24 Georgi Gerganovmetal : use F32 prec for K*Q in vec FA (llama/9595)
2024-09-24 Akarshan BiswasRevert "[SYCL] fallback mmvq (ggml/9088)" (llama/9579)
2024-09-24 R0CKSTARmusa: enable building fat binaries, enable unified...
2024-09-24 Molly SophiaFix merge error in #9454 (llama/9589)
2024-09-24 Johannes GäßlerCUDA: enable Gemma FA for HIP/Pascal (llama/9581)
2024-09-24 Molly SophiaRWKV v6: RWKV_WKV op CUDA implementation (llama/9454)
2024-09-24 slarenggml-alloc : fix list of allocated tensors with GGML_AL...
2024-09-24 agray3Update CUDA graph on scale change plus clear nodes...
2024-09-24 Georgi Gerganovexamples : adapt to ggml.h changes (ggml/0)
2024-09-24 Georgi Gerganovggml : refactoring (llama/#0)
2024-09-24 Georgi Gerganovggml : fix builds (llama/0)
2024-09-24 Georgi Gerganovggml : fix trailing whitespace (llama/0)
2024-09-24 Johannes GäßlerCUDA: fix sum.cu compilation for CUDA < 11.7 (llama...
2024-09-24 slarenggml : fix n_threads_cur initialization with one thread...
2024-09-24 Max Krasnyanskythreadpool : skip polling for unused threads (llama...
2024-09-24 Michael Podvitskiyggml : link MATH_LIBRARY not by its full path (llama...
2024-09-24 Georgi Gerganovcmake : do not hide GGML options + rename option (llama...
2024-09-24 Eveggml : IQ4_NL sgemm + Q4_0 AVX optimization (llama...
2024-09-24 Georgi Gerganovmetal : handle zero-sized allocs (llama/9466)
2024-09-24 Georgi Gerganovcommon : reimplement logging (llama/9418)
2024-09-24 Michael Podvitskiycmake : correct order of sycl flags (llama/9497)
2024-09-24 Michael Podvitskiycmake : try to fix sycl+intel build (llama/9487)
2024-09-24 Yuri Khrustalevggml : ggml_type_name return "NONE" for invalid values...
2024-09-24 Georgi Gerganovcmake : use list(APPEND ...) instead of set() + dedup...
2024-09-24 Dou Xinpengcann: Add host buffer type for Ascend NPU (llama/9406)
2024-09-24 Ahmad Tameemriscv : modify Makefile and add a RISCV_VECT to print...
2024-09-24 Xinpeng Doucann: Fix error when running a non-exist op (llama...
2024-09-24 Johannes GäßlerCUDA: fix --split-mode row race condition (llama/9413)
2024-09-24 R0CKSTARmusa: remove Clang builtins mapping (llama/9421)
2024-09-24 Alberto Cabrera... sycl : update support conditions (llama/9394)
2024-09-24 Georgi Gerganovmetal : fix compile warning with GGML_METAL_NDEBUG...
2024-09-24 Radoslav Gerganovrpc : fix segfault with nkvo (llama/9389)
2024-09-24 Prashant Vithuleggml : vector length agnostic SVE support (llama/9290)
2024-09-24 Johannes GäßlerCUDA: fix variable name conflict for Windows build...
2024-09-24 Markus TavenrathOverlap cmdbuffer creation and cmdbuffer execution...
2024-09-24 Georgi Gerganovcuda : fix FA Q src index (1 -> 0) (llama/9374)
2024-09-24 Neo Zhang Jianyuadd check malloc result on device (llama/9346)
2024-09-24 Johannes Gäßlerggml/examples: add backend support for numerical optimi...
2024-09-24 Georgi Gerganovexamples : add null threadpool args where needed (ggml/0)
next