]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/shortlog
pkg/ggml/sources/whisper.cpp
2025-06-01 Christian Kastnercmake: Factor out CPU architecture detection (llama...
2025-06-01 Vineel Abhinavggml: aarch64: Implement SVE F32 kernels for Mamba...
2025-06-01 Vineel Abhinavggml: aarch64: Implement SVE F32 kernels for vector...
2025-06-01 Johannes GäßlerCUDA: fix FA tg at long context for CC >= 8.9 (llama...
2025-06-01 leo-ponyCANN: Add SOC TYPE printing in cmake configuration...
2025-06-01 lhezopencl: add new ops - `argsort`, `div`, `sub`, `addrows...
2025-06-01 lhezopencl: mark `mul_mat` `f32f32` as supporting non-conti...
2025-06-01 Jeff Bolzvulkan: use timestamp queries for GGML_VULKAN_PERF...
2025-06-01 Akarshan BiswasSYCL: add gelu_erf kernel (llama/13749)
2025-06-01 Xuan-Son Nguyenggml : add ggml_repeat_4d (llama/13824)
2025-06-01 Kai Pastorvulkan : Remove unexpected ; (ggml/1253)
2025-06-01 Kai Pastorcmake : Fix broken CMake error messages (ggml/1252)
2025-06-01 Radoslav Gerganovggml : remove ggml_graph_import and ggml_graph_export...
2025-06-01 KITAITI Makotoruby : add Core ML support (#3214)
2025-05-30 Daniel Beveniusvad : revisit timestamp alignment/mapping (#3173)
2025-05-29 KITAITI Makotoruby : handle build options on installation (#3206)
2025-05-29 Daniel Tangggml : Fix backtrace breaking Windows build (#3203)
2025-05-29 Georgi Gerganovsync : ggml
2025-05-29 Radoslav Gerganovggml : install dynamic backends (ggml/1240)
2025-05-29 Daniel Tangggml : Print backtrace on uncaught C++ exceptions ...
2025-05-29 Daniel Beveniuswhisper : remove whisper_load_backends function (#3196)
2025-05-28 KITAITI Makotoruby : add VAD support, migration to Ruby's newer API...
2025-05-28 Simon Boothwhisper : install shared libs when using GGML_BACKEND_D...
2025-05-28 Fujimoto Seijitests : add a new benchmark test for long-form audio...
2025-05-27 Daniel Beveniusci : update windows-blas uploads action (#3192)
2025-05-27 Georgi Gerganovsync : fix builds - musa, ruby
2025-05-27 Georgi Gerganovtalk-llama : sync llama.cpp
2025-05-27 Georgi Gerganovsync : ggml
2025-05-27 xctanggml : riscv: add xtheadvector support (llama/13720)
2025-05-27 Christian Kastnerggml-cpu: x86 feature detection is specific to x86...
2025-05-27 Diego Devesaggml : allow CUDA graphs when using pipeline parallelis...
2025-05-27 Georgi Gerganovcuda : avoid cuGetErrorString (llama/13791)
2025-05-27 Akarshan BiswasSYCL: Add non contiguous support in RMS_NORM and NORM...
2025-05-27 Romain Biessysycl: Add more debug prints (llama/13640)
2025-05-27 Jeff Bolzvulkan: mark IM2COL as supporting non-contig (llama...
2025-05-27 Bizhao ShiCANN: Add the basic supports of Flash Attention kernel...
2025-05-27 Akarshan BiswasSYCL: revert "sycl: simplify bin_bcast_kernel (ggml...
2025-05-27 Diego Devesaggml-cpu : set openmp wait time if not set (llama/13758)
2025-05-27 Xuan-Son Nguyenggml : add ggml_gelu_erf() CUDA kernel (llama/13719)
2025-05-27 Johannes GäßlerCUDA: fix race condition in FA vector kernels (llama...
2025-05-27 Chenguang LiCANN: Support MUL_MAT_ID for q8_0 and q4_0 (llama/13705)
2025-05-27 Xuan-Son Nguyenggml : fix the order of ggml_unary_op (llama/13718)
2025-05-27 Jeff Bolzvulkan: support CPY from any type to itself (llama...
2025-05-27 Jeff Bolzvulkan: Disable coopmat/coopmat2/bfloat extensions...
2025-05-27 Judduse LOG_WARN to replace `std::cerr` (llama/13657)
2025-05-27 Nicolò Scipionesycl : Remove waits from function calls (llama/13702)
2025-05-27 Ewan CrawfordSYCL: Avoid using with SYCL-Graph for unsupported nodes...
2025-05-27 Henry Linjamäkiopencl: Add support for multiple devices (llama/12622)
2025-05-27 Henry Linjamäkiopencl: fix couple crashes (llama/12795)
2025-05-27 Xuan-Son Nguyenggml : add ggml_gelu_erf() (llama/13667)
2025-05-27 R0CKSTARmusa: Upgrade MUSA SDK version to rc4.0.1 and use mudnn...
2025-05-27 Evevulkan: fix warnings (llama/13626)
2025-05-27 Johannes GäßlerCUDA: skip fully masked-out KV in FA vec kernel (llama...
2025-05-27 Svetlozar Georgievsycl: disable reorder for sycl mulmat (llama/13536)
2025-05-27 Georgi Gerganovmetal : fix typo in FA kernel comments (llama/13651)
2025-05-27 Nicolò Scipionesycl : Overcoming workaround for mmap() allocation...
2025-05-27 0cc4mVulkan: Add f32 accumulator support to quantized mul...
2025-05-27 Georgi Gerganovsync : ggml
2025-05-27 Daniel Beveniusdocs : convert README_sycl.md to utf8 format [no ci...
2025-05-27 Daniel Beveniusnode : enable no_prints to suppress all output (#3189)
2025-05-26 matteng1talk-llama : fix for swedish umlauts + expose model...
2025-05-23 KITAITI Makotodocs : fix VAD section heading levels (#3186)
2025-05-23 Daniel Beveniusci : use dynamic libopenblas.dll for window-blas (...
2025-05-22 Sacha Arbonelserver : Add k6 Load Testing Script (#3175)
2025-05-22 Daniel Beveniusdocs : add VAD model download instructions [no ci]...
2025-05-22 Alpaimdocs : replace typo "]"with ")" in README (#3179)
2025-05-21 Daniel Beveniuswhisper : remove redundant assignments (#3178)
2025-05-20 Jugal Haresh... whisper : update CMakeLists.txt to handle deprecated...
2025-05-19 Daniel Beveniusruby : add GGML_SYCL_DNN option to ruby bindings (...
2025-05-19 Georgi Gerganovtalk-llama : sync llama.cpp
2025-05-19 Georgi Gerganovsync : ggml
2025-05-19 Chenguang LiCANN: Support MOE Model MUL_MAT_ID (llama/13042)
2025-05-19 Gilad S.cmake: use the current build config for vulkan-shaders...
2025-05-19 Jeff Bolzvulkan: move common FA code to flash_attn_base.comp...
2025-05-19 Jeff Bolzvulkan: use scalar FA rather than coopmat2 when N=...
2025-05-19 Georgi Gerganovmetal : add FA-vec kernel for head size 64 (llama/13583)
2025-05-19 Łukasz Ślusarczyksycl : fixed compilation warnings (llama/13582)
2025-05-19 Diego Devesagguf : use ggml log system (llama/13571)
2025-05-19 Atharva Dubeysycl: simplify bin_bcast_kernel (llama/13383)
2025-05-19 Svetlozar Georgievsycl: reordered Q4_K MMVQ (llama/13109)
2025-05-19 Łukasz Ślusarczyksycl: use oneDNN for matrices multiplication (llama...
2025-05-19 Yibo Caiarm64: optimize q6_k_q8_k kernel with i8mm (llama/13519)
2025-05-19 Johannes GäßlerCUDA: fix crash on large batch size for quant. MoE...
2025-05-19 Johannes GäßlerCUDA: faster Deepseek FA, add Turing support (llama...
2025-05-19 bandoticmake: simplify vulkan shader test logic (llama/13263)
2025-05-19 Jeff Bolzvulkan: KHR_coopmat flash attention (llama/13506)
2025-05-19 Jeff Bolzvulkan: workaround FA compile failures on macos (llama...
2025-05-19 Georgi Gerganovmetal : use FA-vec kernel up to batch size 20 (llama...
2025-05-19 Georgi Gerganovmetal : optimize multi-sequence FA vec kernel (llama...
2025-05-19 Dan Johanssonggml-cpu: Update KleidiAI to v1.6 and fix include direc...
2025-05-19 Johannes Gäßlermnist: fix segmentation fault (ggml/1227)
2025-05-19 Diego Devesaggml : fix apple OS check in ggml_print_backtrace ...
2025-05-19 Daniel Tangggml : Fix missing backtrace on Linux (ggml/1228)
2025-05-19 Daniel Beveniusexamples : add vad-speech-segments to win warns [no...
2025-05-16 Daniel Beveniusvad : return early if no vad segments are detected...
2025-05-16 Daniel Beveniusvad : store VAD context in whisper_state (#3156)
2025-05-15 Daniel Beveniuswhisper : add build_*/ to .gitignore [no ci] (#3157)
2025-05-14 Daniel Beveniusexamples : add --print-confidence option to cli (#3150)
2025-05-14 Daniel Beveniusvad : add download-vad-model scripts (#3149)
2025-05-14 Daniel Beveniusserver : add --flash-attn usage output (#3152)
next