]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/shortlog
pkg/ggml/sources/whisper.cpp
2025-02-03 Johannes GäßlerCPU/CUDA: fix (GQA) mul mat back, add CUDA support...
2025-02-03 Bernhard M... cmake : avoid -march=native when reproducible build...
2025-02-03 amd-dwangVulkan-run-test: fix mmq_wg_denoms (llama/11343)
2025-02-03 Jeff Bolzvulkan: sort shaders for more deterministic binary...
2025-02-03 Jeff Bolzvulkan: fix diag_mask_inf (llama/11323)
2025-02-03 Radoslav Gerganovrpc : better caching of the base buffer pointer (llama...
2025-02-03 Georgi Gerganovmetal : fix out-of-bounds write (llama/11314)
2025-02-03 Jeff Bolzvulkan: fix coopmat2 validation failures (llama/11284)
2025-02-03 Nicolò ScipioneSYCL: Introducing memory host pool (llama/11251)
2025-02-03 Georgi Gerganovcmake : add sanitizer flags for llama.cpp (llama/11279)
2025-02-03 Jeff Bolzvulkan: fix coopmat2 flash attention for non-contiguous...
2025-02-03 Radoslav Gerganovrpc : early register backend devices (llama/11262)
2025-02-03 Jeff Bolzvulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1...
2025-02-03 Jeff Bolzvulkan: optimize coopmat2 q4_k/q5_k dequant functions...
2025-02-03 Jeff Bolzvulkan: optimize coopmat2 q2_k dequant function (llama...
2025-02-03 Johannes GäßlerCUDA: backwards pass for misc. ops, add tests (llama...
2025-02-03 fj-y-saitoggml: aarch64: implement SVE kernels for q4_K_q8_K...
2025-02-03 Evevulkan: scale caching for k quants + misc fixes (llama...
2025-02-03 Junil Kimfix: ggml: fix vulkan-shaders-gen build (llama/10448)
2025-02-03 Johannes GäßlerRoPE: fix back, CUDA support for back + noncont. (llama...
2025-02-03 Akarshan BiswasSYCL: Add gated linear attention kernel (llama/11175)
2025-02-03 William Tambelliniggml : add option to not print stack on abort (ggml...
2025-02-03 issixxggml-cpu : fix ggml_graph_compute_thread did not termin...
2025-02-03 Georgi Gerganovci : dummy commit to trigger CI
2025-01-21 KITAITI Makotoruby : Make context accept initial parameters, API... upstream/1.7.4+33
2025-01-18 Corey Earwoodwhisper.objc : fix build and CI
2025-01-14 Georgi Gerganovtalk-llama : sync llama.cpp
2025-01-14 Georgi Gerganovsync : ggml
2025-01-14 Johannes GäßlerGGUF: C++ refactor, backend support, misc fixes (skip...
2025-01-14 lhezggml : add opencl backend (skip) (llama/10693)
2025-01-14 Andreas Kieslingercuda : CUDA Graph Compute Function Refactor (precursor...
2025-01-14 Radoslav Gerganovggml : do not define GGML_USE_CUDA when building with...
2025-01-14 0cc4mVulkan: Fix float16 use on devices without float16...
2025-01-14 Molly Sophiallama: add support for QRWKV6 model architecture (llama...
2025-01-14 Akarshan BiswasSYCL: Refactor ggml_sycl_compute_forward (llama/11121)
2025-01-14 hydaifix: add missing msg in static_assert (llama/11143)
2025-01-14 amritahs-ibmllamafile : ppc64le MMA INT8 implementation (llama...
2025-01-14 Mathieu BaudierDisable GL_KHR_cooperative_matrix Vulkan extension...
2025-01-14 ag2s20150909fix: Vulkan shader gen binary path when Cross-compiling...
2025-01-14 Johannes GäßlerGGUF: C++ refactor, backend support, misc fixes (llama...
2025-01-14 Diego Devesaggml-backend : only offload from host buffers (fix...
2025-01-14 Diego Devesaggml-backend : only offload from host buffers (llama...
2025-01-14 Radoslav Gerganovrpc : code cleanup (llama/11107)
2025-01-14 Akarshan BiswasSYCL: Use get_multi_ptr instead of deprecated get_point...
2025-01-14 Johannes GäßlerCUDA: add BF16 support (llama/11093)
2025-01-14 0cc4mVulkan: Add device-specific blacklist for coopmat for...
2025-01-14 matt23654Support for models with non-512-aligned tensors over...
2025-01-14 Gilad S.fix: Vulkan shader gen binary path (llama/11037)
2025-01-14 Radoslav Gerganovggml : allow loading backend with env variable (ggml...
2025-01-14 Georgi Gerganovscripts : sync opencl, gguf
2025-01-13 Georgi Gerganovwhisper : fix gpu device selection (#2728)
2025-01-13 Georgi Gerganovserver : fix build (#2718)
2025-01-13 Georgi Gerganovtalk-llama : sync llama.cpp (#2709)
2025-01-13 NETZkultur... server : generate unique tmp filenames (#2718)
2025-01-09 Sandro Haneawhisper : add whisper_full_get_segment_no_speech_prob_f...
2025-01-07 Jayantreadme : add docker instructions (#2711)
2025-01-06 Adam Jonesdocs: Fix main -> whisper-cli in download scripts ...
2025-01-06 Georgi Gerganovrelease : v1.7.4 upstream/1.7.4
2025-01-06 Georgi Gerganovci : cont
2025-01-06 Georgi Gerganovci : fix ubuntu runner names
2025-01-04 Yusuf Redžićcli : fix segfault on missing argument (#2700)
2025-01-04 Georgi Gerganovci : fix arm builds
2025-01-04 Georgi Gerganovsync : ggml
2025-01-04 Georgi Gerganovggml : do not install metal source when embed library...
2025-01-04 Georgi Gerganovmetal : avoid uint (llama/11019)
2025-01-04 Srihari-mcwggml : fixes for AVXVNNI instruction set with MSVC...
2025-01-04 Jeff Bolzvulkan: optimize mul_mat for small values of N (llama...
2025-01-04 Jeff Bolzvulkan: im2col and matmul optimizations for stable...
2025-01-04 Jeff Bolzvulkan: Use push constant offset to handle misaligned...
2025-01-04 Evevulkan: multi-row k quants (llama/10846)
2025-01-04 Peterexamples, ggml : fix GCC compiler warnings (llama/10983)
2025-01-04 Djip007ggml : more perfo with llamafile tinyblas on x86_64...
2025-01-04 Diego Devesaggml : use wstring for backend search paths (llama...
2025-01-04 Diego Devesaggml : fix arm enabled features check (llama/10961)
2025-01-04 Diego Devesaggml : fix const usage in SSE path (llama/10962)
2025-01-04 yuri@FreeBSDggml : fix run-time on FreeBSD in get_executable_path...
2025-01-04 Jeff Bolzvulkan: build fixes for 32b (llama/10927)
2025-01-04 Jeff Bolzvulkan: optimize coopmat2 dequant functions (llama...
2025-01-04 Adrien Gallouëtggml-cpu: replace NEON asm with intrinsics in ggml_gemv...
2025-01-04 Akarshan BiswasSYCL: Migrate away from deprecated ggml_tensor->backend...
2025-01-04 Diego Devesaggml : add test for SVE and disable when it fails ...
2025-01-04 Adrien Gallouëtggml: fix arm build with gcc (llama/10895)
2025-01-04 Diego Devesaggml : fix arm build (llama/10890)
2025-01-04 Georgi Gerganovtts : add OuteTTS support (llama/10784)
2025-01-04 Johannes Gäßlertests: add tests for GGUF (llama/10830)
2025-01-04 Daniel Beveniusggml : improve inputs log sched_print_assignments ...
2025-01-02 Samuel Durantereadme : fix real-time audio input example build instru...
2025-01-02 Alterobjc : rename ggml-cpu-aarch64.c to .cpp (#2687)
2025-01-02 Konosuke Sakaidocs : replace Core ML with OpenVINO (#2686)
2024-12-31 Georgi Gerganovmake : fix "main" -> "whisper-cli"
2024-12-31 Nikolaj Olssonci : re-enable Windows cublas build (#2676)
2024-12-30 KITAITI Makotoruby : Fix of C++ header guard name, model URI support...
2024-12-30 Georgi Gerganovexamples : handle "main.exe" deprecation
2024-12-24 Andreas Lubbecli : add --suppress_nst support (#2664)
2024-12-24 Andreas Lubbecli : add no_speech_thold (#2663)
2024-12-23 Georgi Gerganovcmake : remove hardcoded install rpath
2024-12-22 Georgi Gerganovserver : fix help print
2024-12-21 KITAITI Makotoruby : bug fix on callbacks and no_speech_prob (#2656)
2024-12-21 Sacha Arbonelserver : add no-speech threshold parameter and function...
2024-12-21 Georgi Gerganovwhisper : rename suppress_non_speech_tokens to suppress...
next