]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/shortlog
pkg/ggml/sources/whisper.cpp
2025-04-24 Jeff Bolzvulkan: enable coopmat2 FA gqa and split_k optimization...
2025-04-24 Chenguang LiCANN: Add 310P operator support check (llama/12962)
2025-04-24 Georgi Gerganovmetal : add FA-vec kernels for head size 96 (llama...
2025-04-24 hipuddingCANN: Add x86 build ci (llama/12950)
2025-04-24 David HuangCUDA/HIP: Share the same unified memory allocation...
2025-04-24 Akarshan BiswasSYCL: Add ROPE vision kernel (llama/12887)
2025-04-24 Srihari-mcwggml : Add AVX512 implementation of GEMM - Q4_Kx8 ...
2025-04-24 Chenguang LiCANN: Opt ROPE optimization (llama/12865)
2025-04-24 Xinpeng DouCANN: Optimize CANN buffer pool memory management ...
2025-04-24 Akarshan BiswasSYCL: Fix im2col (llama/12910)
2025-04-24 Radoslav Gerganovrpc : use ggml_context_ptr (llama/12938)
2025-04-24 Aclyggml : Depthwise 2D convolution (ggml/1152)
2025-04-24 SXXggml: use _mm[512/256]_dpbusd[_avx]_epi32 to directly...
2025-04-24 Alan Grayggml: disable CUDA graphs for unsupported DUP and CONT...
2025-04-24 Jeff Bolzvulkan: use aligned loads for flash attention mask...
2025-04-24 Ewan Crawfordsycl: Support sycl_ext_oneapi_limited_graph (llama...
2025-04-24 Akarshan BiswasSYCL: Add fp16 type support to unary op kernels (llama...
2025-04-24 Aaron Teoggml: fix compilation error s390x (llama/12848)
2025-04-24 cmdr2cpu: fix cpu backend's supports-op for GET_ROWS_BACK...
2025-04-24 Chenguang LiCANN: Support more ops (llama/12841)
2025-04-24 Prajwal B MehendarkarFixes #12823 (llama/12830)
2025-04-24 Piotr Kubajggml-cpu-impl.h: do not redefine bool on POWER9 (llama...
2025-04-24 Piotr Kubajggml-impl.h: fix build on POWER9 (llama/12855)
2025-04-24 Chenguang LiCANN: Support Opt CONV_TRANSPOSE_1D and ELU (llama...
2025-04-24 Jeff Bolzvulkan: In coopmat2 mmq, load q4_k/q5_k scales through...
2025-04-24 Jeff Bolzvulkan: Use fp16 for the flash attention P*V multiplica...
2025-04-24 Sigbjørn Skjæretcuda : add f32 to bf16 copy op (llama/12806)
2025-04-24 Georgi Gerganovllama : fix FA when KV cache is not used (i.e. embeddin...
2025-04-24 cmdr2ggml: don't include arm_neon.h when using CUDA 12 with...
2025-04-24 Diego Devesaggml : add bilinear upscale support (ggml/1185)
2025-04-24 Diego Devesaggml : add more generic custom op, remove deprecated...
2025-04-24 Neo Zhang JianyuRevert "sycl:remove redundant memcopy in function ggml_...
2025-04-24 lhezopencl: better identify Adreno GPU (llama/12760)
2025-04-24 Georgi Gerganovcuda : fix HIP and MUSA BF16 (llama/0)
2025-04-24 zhouwgsycl: remove redundant memcopy in function ggml_backend...
2025-04-24 zhouwgCANN: fix typo in ggml-cann (llama/12733)
2025-04-24 hipuddingCANN: Refactor to reduce duplicate code (llama/12731)
2025-04-24 R0CKSTARmusa: fix compilation warnings in mp_22/31 (llama/12780)
2025-04-24 Jeff Bolzvulkan: fix NaN issue in flash attention shader (llama...
2025-04-24 Jeff Bolzvulkan: Use unclamped loads for flash attention mask...
2025-04-24 0cc4mVulkan: Tune Vulkan mmq int dot shader for performance...
2025-04-24 Nicolò Scipionesycl: allow ggml-sycl configuration and compilation...
2025-04-24 Ronny Brendelcmake: fix ggml-shaders-gen compiler paths containing...
2025-04-24 Jeff Bolzvulkan: Hybrid waitForFences/getFenceStatus to reduce...
2025-04-24 Jeff Bolzvulkan: set cmake minimum and project name in vulkan...
2025-04-24 Gaurav GargCUDA: Prefer vector flash decoding kernel for Gemma...
2025-04-24 Jeff Bolzvulkan: Fix missing cmake logic for dot product extensi...
2025-04-24 a3shfix MUSA compiler warning (llama/12704)
2025-04-24 Chenguang LiCANN: Support operator SIN COS ARGMAX (llama/12709)
2025-04-24 Alan GraySimplify and improve CUDA graphs through use of indirec...
2025-04-24 hipuddingCANN: Fix failed test cases (llama/12708)
2025-04-24 lhezopencl: use `max_alloc_size` in backend ctx instead...
2025-04-24 Jeff Bolzvulkan: Implement split_k for coopmat2 flash attention...
2025-04-24 bandoticmake: remove caching from vulkan coopmat checks (llama...
2025-04-24 Jeff Bolzvulkan: Implement grouped query attention in the coopma...
2025-04-24 0cc4mVulkan: Fix mmq int dot float cache size (llama/12722)
2025-04-24 Diego Devesallama : add option to override model tensor buffers...
2025-04-24 Georgi Gerganovggml : simplify Arm fp16 CPU logic (ggml/1177)
2025-04-24 Sigbjørn SkjæretCUDA: don't convert BF16 weights to FP32 (ggml/1174)
2025-04-23 Daniel Beveniuscoreml : set convert_to="mlprogram" in convert
2025-04-22 Daniel Beveniusci : disable freeBSD job in build.yml (#3064)
2025-04-20 Daniel Beveniusexamples : add HEAPU8 to exported runtime methods ...
2025-04-17 KITAITI Makotoruby : make Ruby bindings installed with build options...
2025-04-16 Sacha Arbonelwhisper : add no_context parameter to whisper_params...
2025-04-15 Fujimoto Seijiexamples : add FFmpeg v7.0 support to ffmpeg-transcode...
2025-04-14 KITAITI Makotoruby: use CMake in build process (#3043)
2025-04-11 Jeff Klassendocs : update README.md to note newer nvidia gpus ...
2025-04-11 Lin Xiaodongaddon.node : support max_context api for addon.node...
2025-04-11 Georgi Gerganovwhisper : reduce delta_min from 1000ms to 100ms (#3028)
2025-04-10 Fujimoto Seijidocs : document how to use 'WHISPER_FFMPEG' build optio...
2025-04-09 Ekaitz Zárragadocs : fix README.md (#3024)
2025-04-09 Daniel Beveniusxcf : use check for visionos build version (#3021)
2025-04-09 Olliruby : fix types of arguments for rb_get_kwargs in...
2025-04-08 Olliruby : Update uri.rb (#3016)
2025-04-06 Greg Sadetskymodels : fix dead link to models in readme (#3006)
2025-04-05 KITAITI Makotoruby : change homepage URI in Ruby gemspec (#3007)
2025-04-04 Fujimoto Seijitests : add script to benchmark whisper.cpp on LibriSpe...
2025-04-04 Fujimoto Seijiwhisper : fix "bench-all outputs an invalid result...
2025-04-04 Georgi Gerganovrename : ggerganov -> ggml-org (#3005)
2025-04-04 Daniel Beveniusexamples : update server.py to match github pages app...
2025-04-03 Daniel Beveniuswhisper.wasm : fix unknown language issue (#3000)
2025-04-03 Georgi Gerganovexamples : add new sources
2025-04-03 Georgi Gerganovsync : ggml
2025-04-03 cmdr2cpu: move all the operators into a separate c++ file...
2025-04-03 Daniel Beveniusdocs : add xcframework section to README.md [no ci...
2025-04-02 Georgi Gerganovreadme : update roadmap link
2025-04-02 Georgi Gerganovrelease : v1.7.5 upstream/1.7.5
2025-04-02 Georgi Gerganovbench : update numbers [no ci] (#2993)
2025-04-02 Georgi Gerganovsync : ggml
2025-04-02 Chenguang Liget_rows and dup optimization (llama/12671)
2025-04-02 Junil Kimopencl : fix memory allocation size (llama/12649)
2025-04-02 Georgi Gerganovmetal : use F32 prec in FA kernels (llama/12688)
2025-04-02 R0CKSTARFix clang warning in gguf_check_reserved_keys (llama...
2025-04-02 Wagner Brunavulkan: fix build when glslc doesn't support coopmat...
2025-04-02 Romain BiessySYCL: Rename oneMKL to oneMath (llama/12192)
2025-04-02 Akarshan BiswasSYCL: switch to SYCL namespace (llama/12674)
2025-04-02 a3shggml : faster ssm scan (llama/10558)
2025-04-02 0cc4mVulkan: Add DP4A MMQ and Q8_1 quantization shader ...
2025-04-02 Georgi Gerganovcmake : fix whitespace (llama/0)
2025-04-02 Daniel Beveniustests : remove gh label test-whisper-cli-tiny-en (...
next