]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/shortlog
pkg/ggml/sources/whisper.cpp
2024-09-20 Stavros Panakakisgo : add tests and update bindings (#2425)
2024-09-17 Toliverserver : use OS-generated temp file name for converted...
2024-09-15 Binozogo : fix CUDA build (#2416)
2024-09-11 Mengqing Caocann : add Ascend NPU instructions (#2410)
2024-09-07 Philippe Normandcmake: Fix libdir value in pkgconfig file (#2407)
2024-09-02 Georgi Gerganovrevert : cmake : set MSVC to use UTF-8 on source files...
2024-09-02 Georgi Gerganovsync : ggml
2024-09-02 Johannes Gäßlerggml: fix ggml_graph_cpy undefined behavior (ggml/943)
2024-09-02 Georgi Gerganovcann : fix doxy (ggml/0)
2024-09-02 Georgi Gerganovvulkan : fix build (llama/0)
2024-09-02 Georgi Gerganovcuda : mark BF16 CONT as unsupported
2024-09-02 Salvatore Mesoracaggml : fix cont with transposed tensors when one dimens...
2024-08-30 Tim Millercmake : set MSVC to use UTF-8 on source files (#2346)
2024-08-30 UsernamesLamereadme : remove invalid flag from Python example (...
2024-08-30 Georgi Gerganovreadme : fix link (#2394)
2024-08-28 hsinhoyehgo : add beamsize/entropythold/maxcontext to context...
2024-08-28 Georgi Gerganovtalk-llama : sync llama.cpp
2024-08-28 Georgi Gerganovwhisper : update FA call
2024-08-28 Georgi Gerganovsync : ggml
2024-08-28 Georgi Gerganovsync : vulkan (skip) (llama/0)
2024-08-28 slarenggml : do not crash when quantizing q4_x_x with an...
2024-08-28 Georgi Gerganovmetal : separate scale and mask from QKT in FA kernel...
2024-08-28 Georgi Gerganovggml : add SSM Metal kernels (llama/8546)
2024-08-28 slarenmetal : gemma2 flash attention support (llama/9159)
2024-08-28 Johannes GäßlerCPU/CUDA: Gemma 2 FlashAttention support (llama/8542)
2024-08-28 Akarshan BiswasAdd a space to supress a cmake warning (llama/9133)
2024-08-28 luoyu-intelAdd oneDNN primitive support (llama/9091)
2024-08-28 compiladellama : simplify Mamba with advanced batch splits ...
2024-08-28 Meng, Hengyufallback mmvq (llama/9088)
2024-08-28 zhentaoyuFix SYCL `im2col` and `convert` Overflow with Large...
2024-08-28 Radoslav Gerganovrpc : print error message when failed to connect endpoi...
2024-08-28 Radoslav Gerganovrpc : prevent crashes on invalid input (llama/9040)
2024-08-28 Nico Bosshardggml : dynamic ggml_sched_max_splits based on graph_siz...
2024-08-28 Georgi Gerganovcmake : remove unused option GGML_CURL (llama/9011)
2024-08-28 Daniel Beveniusggml : move rope type enum to ggml.h (llama/8949)
2024-08-28 DavidKorczynskiggml: fix div-by-zero (llama/9003)
2024-08-28 Markus TavenrathOptimize Vulkan backend for better CPU performance...
2024-08-28 Johannes Gäßlerfeat: ref. cross entropy, add CUDA, fix grad test ...
2024-08-28 Johannes Gäßlerggml: remove bad assert (ggml/928)
2024-08-28 Johannes Gäßlerexamples: add MNIST training + missing ops
2024-08-28 Brad Murraymodels : add support for wget2 for fedora (#2387)
2024-08-28 Pengreadme : update the path to bench.py (#2386)
2024-08-28 Ivo von Putzer... readme : fix typo (#2383)
2024-08-28 stormoficereadme : fix broken links in implementation details...
2024-08-28 Georgi Gerganovwhisper : fix compile warning for unused params
2024-08-21 Georgi Gerganovsync : ggml vulkan (ggml/0)
2024-08-21 Radoslav Gerganovyolo : add backend support (ggml/924)
2024-08-21 Daniel Beveniusggml : fix typo in ggml-quants.c comment (ggml/922)
2024-08-21 Ronsorfeat: add new `sin` and `cos` operators (ggml/919)
2024-08-20 Eric Curtinreadme : fix broken links (#2358)
2024-08-20 Justine Tunneyexamples : use colorblind friendly TTY color scheme...
2024-08-12 Georgi Gerganovsync : ggml
2024-08-12 Salvatore Mesoracaggml : support forward pass broadcasting in ggml_sub...
2024-08-12 slarenmetal : fix uninitialized abort_callback (llama/8968)
2024-08-12 Georgi Gerganovrpc : sanitize tensor data + warnings (llama/0)
2024-08-09 Mengqing Caocann : add Ascend NPU support (#2336)
2024-08-09 Georgi Gerganovwhisper : fix compile warning (#0)
2024-08-09 Georgi Gerganovsync : ggml
2024-08-09 hipuddingggml : add CANN backend (llama/0)
2024-08-09 Georgi Gerganovscripts : sync cann
2024-08-08 Georgi Gerganovci : disable ruby workflow (#0)
2024-08-08 Georgi Gerganovci : try to fix FreeBSD (#0)
2024-08-08 Georgi Gerganovbuild : fix aarch64 (#0)
2024-08-08 Georgi Gerganovtalk-llama : sync llama.cpp
2024-08-08 Georgi Gerganovsync : ggml
2024-08-08 slarenggml-backend : fix async copy from CPU (llama/8897)
2024-08-08 Ouadie EL FAROUKIUpdated SYCL device filtering (llama/8901)
2024-08-08 Johannes GäßlerCUDA/HIP: fix tests/test-backend-ops (llama/8896)
2024-08-08 Johannes GäßlerCUDA: fix padding logic for FP16/FP32 (llama/8884)
2024-08-08 Molly Sophiaggml : add epsilon as a parameter for group_norm (llama...
2024-08-08 Justine Tunneyggml : fix overflows in elu function (llama/8866)
2024-08-08 jdomkeggml : reading the runtime sve config of the cpu (llama...
2024-08-08 Sigbjørn SkjæretFix conversion of unnormalized BF16->BF16 weights ...
2024-08-08 Ouadie EL FAROUKIFixing wrong VDR iq4nl value (llama/8812)
2024-08-08 matteoggml-cuda: Adding support for unified memory (llama...
2024-08-08 Alex O'ConnellBuild: Only include execinfo.h on linux systems that...
2024-08-08 slarencuda : fix dmmv cols requirement to 2*GGML_CUDA_DMMV_X...
2024-08-08 l3utterflyadded android implementation of ggml_print_backtrace_sy...
2024-08-08 wangshuai09cann: update cmake (llama/8765)
2024-08-08 zhentaoyuAdd `TIMESTEP_EMBEDDING` OP (llama/8707)
2024-08-08 CarterLi999ggml: bugfix: fix the inactive elements is agnostic...
2024-08-08 R0CKSTARcuda : organize vendor-specific headers into vendors...
2024-08-08 Meng, Hengyuadd conv support (llama/8688)
2024-08-08 R0CKSTARfeat: Support Moore Threads GPU (llama/8383)
2024-08-08 Borislav Stanimirovggml : ignore more msvc warnings (ggml/906)
2024-08-08 Georgi Gerganovmetal : fix struct name (ggml/912)
2024-08-08 Conrad Kramermetal : add abort callback (ggml/905)
2024-08-08 0cc4mvulkan : implement Stable Diffusion operators (ggml...
2024-08-08 Daniel Beveniusggml : move c parameter comment to ggml_rope_ext (ggml...
2024-08-08 Georgi Gerganovggml : resolve sync conflicst (ggml/0)
2024-08-08 Georgi Gerganovcommon : handle new quant types (ggml/0)
2024-08-08 Dibakar Gopeggml : add ggml-aarch64 (ggml/0)
2024-08-08 slarenggml : reduce hash table reset cost (llama/8698)
2024-08-08 DavidKorczynskiggml: handle ggml_init failure to fix NULL pointer...
2024-08-08 Chen Xifix multi-gpu issue on sycl (llama/8554)
2024-08-08 Georgi Gerganovggml : add and use ggml_cpu_has_llamafile() (llama...
2024-08-08 Joe ToddRe-add erroneously removed -fsycl from GGML_EXTRA_LIBS...
2024-08-08 Joe Toddsycl : Add support for non-release DPC++ & oneMKL ...
2024-08-08 0cc4mVulkan IQ4_NL Support (llama/8613)
2024-08-08 Jeroen MostertAllow all RDNA2 archs to use sdot4 intrinsic (llama...
next