]> git.djapps.eu Git - pkg/ggml/sources/ggml/shortlog
pkg/ggml/sources/ggml
2025-04-08 Alan GraySimplify and improve CUDA graphs through use of indirec...
2025-04-08 hipuddingCANN: Fix failed test cases (llama/12708)
2025-04-08 lhezopencl: use `max_alloc_size` in backend ctx instead...
2025-04-08 Jeff Bolzvulkan: Implement split_k for coopmat2 flash attention...
2025-04-08 bandoticmake: remove caching from vulkan coopmat checks (llama...
2025-04-08 Jeff Bolzvulkan: Implement grouped query attention in the coopma...
2025-04-08 0cc4mVulkan: Fix mmq int dot float cache size (llama/12722)
2025-04-08 Diego Devesallama : add option to override model tensor buffers...
2025-04-07 Georgi Gerganovggml : simplify Arm fp16 CPU logic (#1177)
2025-04-04 Sigbjørn SkjæretCUDA: don't convert BF16 weights to FP32 (#1174)
2025-04-03 Georgi Gerganovsync : whisper.cpp upstream/0.0.1898
2025-04-02 cmdr2cpu: move all the operators into a separate c++ file...
2025-04-02 Georgi Gerganovsync : llama.cpp
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)
2025-03-31 Georgi Gerganovsync : whisper.cpp
2025-03-31 Sandro Haneacmake: improve Vulkan cooperative matrix support checks...
2025-03-31 Georgi Gerganovsync : llama.cpp
2025-03-31 Akarshan BiswasSYCL: Remove misleading ggml_sycl_op_flatten function...
2025-03-31 Georgi Gerganovmetal : use constexpr in FA kernels + fix typedef ...
2025-03-31 R0CKSTARmusa: fix all warnings, re-enable `-DLLAMA_FATAL_WARNIN...
2025-03-31 Jaycmake : fix ccache conflict (llama/12522)
2025-03-29 Xuan-Son Nguyencpu : rm unused variable (#1166)
2025-03-29 cmdr2cpu: de-duplicate some of the operators and refactor...
2025-03-28 Georgi Gerganovsync : whisper.cpp
2025-03-28 Daniel Beveniusggml : add logging for native build options/vars (whisp...
2025-03-28 Daniel Beveniusexamples : command.wasm updates (whisper/2904)
2025-03-28 Georgi Gerganovsync : llama.cpp
2025-03-28 Georgi Gerganovmetal : improve FA + improve MoE (llama/12612)
2025-03-28 Icenowy Zhengvulkan: fix coopmat shader generation when cross-compil...
2025-03-28 amritahs-ibmllamafile : ppc64le GEMV forwarding for FP32. (llama...
2025-03-28 Radoslav Gerganovrpc : send hash when tensor data is above some fixed...
2025-03-28 lhezopencl: add multi and vision rope, `gelu_quick` and...
2025-03-27 Georgi Gerganovsync : llama.cpp
2025-03-27 Georgi Gerganovscripts : update sync (#1161)
2025-03-27 Georgi Gerganovfiles : remove old wkv6 sources (#0)
2025-03-27 Georgi Gerganovsync : llama.cpp
2025-03-27 Georgi Gerganovggml : sync/merge cmake,riscv,powerpc, add common.cmake...
2025-03-27 amritahs-ibmllamafile : ppc64le MMA implementation for Q4_0. (llama...
2025-03-27 Akarshan BiswasSYCL: implement memset ggml backend buffer interface...
2025-03-27 Slobodan JosicHIP: Add support for RDNA4 targets (llama/12372)
2025-03-27 Georgi Gerganovmetal : refactor mat-vec code (llama/12569)
2025-03-27 Georgi Gerganovggml : fix MUL_MAT_ID repack with Q8_K (llama/12544)
2025-03-27 Dan Johanssonggml-cpu : update KleidiAI to v1.5.0 (llama/12568)
2025-03-27 Akarshan BiswasSYCL: disable Q4_0 reorder optimization (llama/12560)
2025-03-27 lhezopencl: simplify kernel embedding logic in cmakefile...
2025-03-27 R0CKSTARCUDA: Fix clang warnings (llama/12540)
2025-03-27 Jeff Bolzvulkan: fix mul_mat_vec failure in backend tests (llama...
2025-03-27 Georgi Gerganovggml : fix quantized cpy op (llama/12310)
2025-03-27 R0CKSTARmusa: refine compute capability (llama/12493)
2025-03-27 Jeff Bolzvulkan: Optimize mul_mat_vec p021 and nc shaders (llama...
2025-03-27 stduhpfVulkan: RTE rounding for cpy to quant (llama/12480)
2025-03-27 Evevulkan: workaround for AMD Windows driver 16 bit unpack...
2025-03-27 蕭澧邦Fix build on Windows when ccache enabled (#9954) (llama...
2025-03-27 Svetlozar Georgievsycl: cleanup oneDNN related code (llama/12097)
2025-03-27 Srihari-mcwggml : block interleaving support for Q4_K quantization...
2025-03-27 Gaurav GargCUDA: Improve flash decoding kernel GPU occupancy for...
2025-03-27 Jeff Bolzvulkan: optimize iq1 coopmat2 dequant functions (llama...
2025-03-27 Guus WaalsFix visionOS build and add CI (llama/12415)
2025-03-27 Jeff Bolzvulkan: Submit once enough matmul work has been recorde...
2025-03-27 lhezopencl: improve profiling (llama/12442)
2025-03-27 R0CKSTARmusa: override warp_size of musa device to 32 (llama...
2025-03-27 Łukasz ŚlusarczykSYCL: using graphs is configurable by environment varia...
2025-03-27 fj-y-saitoggml : add SVE support for q6_K_q8_K (llama/12361)
2025-03-27 0cc4mVulkan: Default to 1GB allocations instead of 4GB to...
2025-03-27 Łukasz Ślusarczykfixed compilation warnings in ggml-sycl (llama/12424)
2025-03-27 Molly Sophiallama: Add support for RWKV v7 architecture (llama...
2025-03-27 Gaurav Gargcuda : enable CUDA Graph on CUDA Toolkit < 12.x (llama...
2025-03-27 Guus Waalsggml-vulkan: remove unused find_program(glslc) (llama...
2025-03-27 Jeff Bolzvulkan: Add N/2 and N/4 optimized paths in coopmat2...
2025-03-27 Danielevulkan: subgroup size tuning (llama/12087)
2025-03-27 Jeff Bolzvulkan: use fp32 in coopmat2 q4_k dequant function...
2025-03-27 Jeff Bolzvulkan: Pad N dimension of B matrix for coopmat2 perf...
2025-03-27 Jeff Bolzvulkan: Adjust coopmat2 tile sizes and selection heuris...
2025-03-27 Christian Kastnercmake : enable building llama.cpp using system libggml...
2025-03-27 Akarshan BiswasSYCL: set extras only on GGML_TYPE_Q4_0 (llama/12366)
2025-03-27 aubreyliSYCL: Delete redundant plus sign and space (llama/12391)
2025-03-27 fairydreamingSYCL : support non-contiguous tensors in binary ops...
2025-03-27 Chenguang LiMUL_MAT optimization (llama/12382)
2025-03-27 Alberto Cabrera... sycl : variable sg_size support for mmvq kernels (llama...
2025-03-27 uvosCUDA/HIP: Fix fattn-vec-* when device warp size is...
2025-03-27 Jeff Bolzvulkan: fix bug in coopmat1 mul_mat_id (llama/12316)
2025-03-27 uvosCUDA/HIP: refractor mmqv to unify the calculation of...
2025-03-27 jklincnggml-backend : fix backend search path (llama/12330)
2025-03-27 BB-fatmetal : Cache the Metal library at the device context...
2025-03-27 Evemat vec double buffer (llama/12188)
2025-03-27 R0CKSTARmusa: support new arch mp_31 and update doc (llama...
2025-03-27 Henry Linjamäkiopencl: use OpenCL C standard supported by the device...
2025-03-27 Georgi Gerganovtests : fix test-quantize-fns to init the CPU backend...
2025-03-27 Jason C.Hggml-backend : make path_str compatible with C++20...
2025-03-27 Daniel Beveniusggml : skip intermediate .air file when compiling ...
2025-03-26 Akarshan Biswasci: disable test-opt for now (#1158)
next