| 2024-07-27 |
0cc4m | Vulkan MMQ Fix (llama/8479) |
commit | commitdiff | tree |
| 2024-07-27 |
bandoti | vulkan : cmake integration (llama/8119) |
commit | commitdiff | tree |
| 2024-07-27 |
Georgi Gerganov | metal : template-ify some of the kernels (llama/8447) |
commit | commitdiff | tree |
| 2024-07-27 |
Georgi Gerganov | ggml : minor naming changes (llama/8433) |
commit | commitdiff | tree |
| 2024-07-27 |
Chen Xi | fix the mul_mat_id ut issues (llama/8427) |
commit | commitdiff | tree |
| 2024-07-27 |
Nicholai Tukanov | ggml : add NVPL BLAS support (#8329) (llama/8425) |
commit | commitdiff | tree |
| 2024-07-27 |
Daniel Bevenius | cuda : suppress 'noreturn' warn in no_device_code ... |
commit | commitdiff | tree |
| 2024-07-27 |
Johannes Gäßler | CUDA: optimize and refactor MMQ (llama/8416) |
commit | commitdiff | tree |
| 2024-07-27 |
AidanBeltonS | Use multi_ptr to clean up deprecated warnings (llama... |
commit | commitdiff | tree |
| 2024-07-27 |
Georgi Gerganov | ggml : move sgemm sources to llamafile subfolder (llama... |
commit | commitdiff | tree |
| 2024-07-27 |
Dibakar Gope | ggml : add AArch64 optimized GEMV and GEMM Q4 kernels... |
commit | commitdiff | tree |
| 2024-07-27 |
Alberto Cabrera... | sycl : Reenabled mmvq path for the SYCL Nvidia Backend... |
commit | commitdiff | tree |
| 2024-07-27 |
Alberto Cabrera... | sycl : fix powf call in device code (llama/8368) |
commit | commitdiff | tree |
| 2024-07-25 |
Mahesh Madhav | ggml : loop tiling optimizations for scalar path (... |
commit | commitdiff | tree |
| 2024-07-22 |
Ivan Filipov | ggml: add support for float16 input tensors in pooling... |
commit | commitdiff | tree |
| 2024-07-22 |
Brian | gguf.md: naming convention synced to llama.cpp (#896) |
commit | commitdiff | tree |
| 2024-07-21 |
Brian | gguf.md: kv store has new authorship metadata keys... |
commit | commitdiff | tree |
| 2024-07-20 |
Tony Wasserka | vulkan : initialize vk_buffer_struct members to VK_NULL... |
commit | commitdiff | tree |
| 2024-07-20 |
Georgi Gerganov | py : update pacakges + fix yolo warning |
commit | commitdiff | tree |
| 2024-07-12 |
Borislav Stanimirov | cmake : only enable GGML_NATIVE and x86 flags if not... |
commit | commitdiff | tree |
| 2024-07-08 |
Georgi Gerganov | sync : whisper.cpp |
commit | commitdiff | tree |
| 2024-07-08 |
Georgi Gerganov | examples : fix compile warnings [no ci] (whisper/0) |
commit | commitdiff | tree |
| 2024-07-08 |
Daniel Bevenius | ggml : remove unnecessary UNUSED macro call (#880) |
commit | commitdiff | tree |
| 2024-07-08 |
Georgi Gerganov | sync : llama.cpp |
commit | commitdiff | tree |
| 2024-07-08 |
Georgi Gerganov | tests : fix whitespace (llama/0) |
commit | commitdiff | tree |
| 2024-07-08 |
Natsu | cmake : add GGML_BUILD and GGML_SHARED macro definition... |
commit | commitdiff | tree |
| 2024-07-08 |
Ouadie EL FAROUKI | Enabled more data types for oneMKL gemm_batch (llama... |
commit | commitdiff | tree |
| 2024-07-08 |
Johannes Gäßler | CUDA: MMQ support for iq4_nl, iq4_xs (llama/8278) |
commit | commitdiff | tree |
| 2024-07-08 |
Daniele | CUDA: revert part of the RDNA1 optimizations (llama... |
commit | commitdiff | tree |
| 2024-07-08 |
Johannes Gäßler | CUDA: fix MMQ stream-k rounding if ne00 % 128 != 0... |
commit | commitdiff | tree |
| 2024-07-08 |
luoyu-intel | Fix WARP_SIZE=16 bug of Intel GPU (llama/8266) |
commit | commitdiff | tree |
| 2024-07-08 |
Neo Zhang Jianyu | rm get_work_group_size() by local cache for performance... |
commit | commitdiff | tree |
| 2024-07-08 |
AidanBeltonS | Remove unneeded semicolons (llama/8280) |
commit | commitdiff | tree |
| 2024-07-08 |
Daniele | Define and optimize RDNA1 (llama/8085) |
commit | commitdiff | tree |
| 2024-07-08 |
Judd | fix typo (llama/8267) |
commit | commitdiff | tree |
| 2024-07-08 |
AidanBeltonS | Dequant improvements rebase (llama/8255) |
commit | commitdiff | tree |
| 2024-07-08 |
Clint Herron | Removes multiple newlines at the end of files that... |
commit | commitdiff | tree |
| 2024-07-08 |
slaren | cuda : update supports_op for matrix multiplication... |
commit | commitdiff | tree |
| 2024-07-08 |
luoyu-intel | Fix win build conflict of math library (llama/8230) |
commit | commitdiff | tree |
| 2024-07-08 |
luoyu-intel | Fix the sub group size of Intel (llama/8106) |
commit | commitdiff | tree |
| 2024-07-08 |
Johannes Gäßler | CUDA: refactor and optimize IQ MMVQ (llama/8215) |
commit | commitdiff | tree |
| 2024-07-08 |
zhentaoyu | Update SYCL-Rope op and Refactor (llama/8157) |
commit | commitdiff | tree |
| 2024-07-08 |
Johannes Gäßler | CUDA: fix MMQ stream-k for --split-mode row (llama... |
commit | commitdiff | tree |
| 2024-07-02 |
slaren | fix uses of GGML_USE_CUBLAS in tests and examples ... |
commit | commitdiff | tree |
| 2024-07-02 |
John Balis | feat: cuda implementation for `ggml_conv_transpose_1d... |
commit | commitdiff | tree |
| 2024-06-30 |
Yilong Guo | sycl : add build instruction (#870) |
commit | commitdiff | tree |
| 2024-06-30 |
John Balis | update "Using cuBLAS" to use correct update cuda compil... |
commit | commitdiff | tree |
| 2024-06-26 |
Georgi Gerganov | sync : whisper.cpp |
commit | commitdiff | tree |
| 2024-06-26 |
Georgi Gerganov | whisper : disable CUDA mel + fix FFMPEG |
commit | commitdiff | tree |
| 2024-06-26 |
Georgi Gerganov | sync : llama.cpp |
commit | commitdiff | tree |
| 2024-06-26 |
slaren | ggml : add GGML_CUDA_USE_GRAPHS option, restore GGML_CU... |
commit | commitdiff | tree |
| 2024-06-26 |
Georgi Gerganov | sync : llama.cpp, whisper.cpp |
commit | commitdiff | tree |
| 2024-06-26 |
Georgi Gerganov | ggml : reorganize source code + improve CMake (#865) |
commit | commitdiff | tree |
| 2024-06-21 |
Georgi Gerganov | files : remove old (#0) |
commit | commitdiff | tree |
| 2024-06-18 |
Georgi Gerganov | sync : whisper.cpp |
commit | commitdiff | tree |
| 2024-06-18 |
Georgi Gerganov | whisper : use ggml_backend_sched (whisper/2239) |
commit | commitdiff | tree |
| 2024-06-16 |
Georgi Gerganov | sync : whisper.cpp |
commit | commitdiff | tree |
| 2024-06-16 |
Georgi Gerganov | cuda : fix bounds check for src0 rows in MMVQ kernel... |
commit | commitdiff | tree |
| 2024-06-16 |
Borislav Stanimirov | whisper : remove `speed_up` and `phase_vocoder*` functi... |
commit | commitdiff | tree |
| 2024-06-16 |
William Tambellini | examples : add support for decoding input with ffmpeg... |
commit | commitdiff | tree |
| 2024-06-16 |
Georgi Gerganov | examples : remove whisper (#860) |
commit | commitdiff | tree |
| 2024-06-16 |
slaren | move BLAS to a separate backend (cont) (llama/6210) |
commit | commitdiff | tree |
| 2024-06-16 |
Georgi Gerganov | scripts : sync ggml-blas |
commit | commitdiff | tree |
| 2024-06-16 |
0cc4m | Vulkan Shader Refactor, Memory Debugging Option (llama... |
commit | commitdiff | tree |
| 2024-06-16 |
Georgi Gerganov | ggml : remove OpenCL (#0) |
commit | commitdiff | tree |
| 2024-06-16 |
Georgi Gerganov | cmake : fix cuda vars (#0) |
commit | commitdiff | tree |
| 2024-06-16 |
Georgi Gerganov | scripts : update sync |
commit | commitdiff | tree |
| 2024-06-16 |
Hong Bo PENG | ggml : fix and optimize ppc64le (#849) |
commit | commitdiff | tree |
| 2024-06-16 |
Daniel Bevenius | ggml : remove duplicate include of ggml-common.h (... |
commit | commitdiff | tree |
| 2024-06-16 |
Yilong Guo | sycl : remove global variables (cont) (llama/7710) |
commit | commitdiff | tree |
| 2024-06-16 |
Yilong Guo | scripts : add ggml-sycl to sync scripts (#857) |
commit | commitdiff | tree |
| 2024-06-15 |
Georgi Gerganov | ci : add GG_BUILD_NO_DOWNLOAD |
commit | commitdiff | tree |
| 2024-06-15 |
Georgi Gerganov | ggml : remove opencl (#0) |
commit | commitdiff | tree |
| 2024-06-15 |
Georgi Gerganov | cuda : update build (#0) |
commit | commitdiff | tree |
| 2024-06-15 |
Georgi Gerganov | sync : llama.cpp |
commit | commitdiff | tree |
| 2024-06-15 |
Georgi Gerganov | tests : adapt to changes (#0) |
commit | commitdiff | tree |
| 2024-06-15 |
Meng, Hengyu | remove global variables (llama/7710) |
commit | commitdiff | tree |
| 2024-06-15 |
Johannes Gäßler | CUDA: faster q2_K, q3_K MMQ + int8 tensor cores (llama... |
commit | commitdiff | tree |
| 2024-06-15 |
Georgi Gerganov | metal : utilize max shared memory for mul_mat_id (llama... |
commit | commitdiff | tree |
| 2024-06-15 |
Radoslav Gerganov | rpc : fix ggml_backend_rpc_supports_buft() (llama/7918) |
commit | commitdiff | tree |
| 2024-06-15 |
slaren | move BLAS to a separate backend (llama/6210) |
commit | commitdiff | tree |
| 2024-06-15 |
Johannes Gäßler | CUDA: fix broken oob check for FA vec f32 kernel (llama... |
commit | commitdiff | tree |
| 2024-06-15 |
Georgi Gerganov | tests : add non-cont unary tests (llama/7857) |
commit | commitdiff | tree |
| 2024-06-15 |
Georgi Gerganov | ggml : improve ggml_is_contiguous logic (llama/7856) |
commit | commitdiff | tree |
| 2024-06-15 |
k.h.lai | vulkan: select only one device for single gpu with... |
commit | commitdiff | tree |
| 2024-06-15 |
0cc4m | Update Vulkan RoPE implementation (llama/7818) |
commit | commitdiff | tree |
| 2024-06-15 |
Johannes Gäßler | CUDA: int8 tensor cores for MMQ (q4_K, q5_K, q6_K)... |
commit | commitdiff | tree |
| 2024-06-15 |
Johannes Gäßler | CUDA: use tensor cores for MMQ (llama/7676) |
commit | commitdiff | tree |
| 2024-06-15 |
Ben Ashbaugh | use the correct SYCL context for host USM allocations... |
commit | commitdiff | tree |
| 2024-06-15 |
Johannes Gäßler | CUDA: revise q8_1 data layout for mul_mat_q (llama... |
commit | commitdiff | tree |
| 2024-06-15 |
slaren | vulkan : reuse parent extra for views (llama/7806) |
commit | commitdiff | tree |
| 2024-06-15 |
pengxin99 | fix softmax r2r result wrong issue (llama/7811) |
commit | commitdiff | tree |
| 2024-06-15 |
Johannes Gäßler | CUDA: refactor mmq, dmmv, mmvq (llama/7716) |
commit | commitdiff | tree |
| 2024-06-15 |
Georgi Gerganov | ggml : refactor rope norm/neox (llama/7634) |
commit | commitdiff | tree |
| 2024-06-15 |
agray3 | Allow number of nodes in CUDA graph to change (llama... |
commit | commitdiff | tree |
| 2024-06-15 |
Georgi Gerganov | ggml : remove OpenCL (llama/7735) |
commit | commitdiff | tree |
| 2024-06-15 |
Georgi Gerganov | ggml : prevent builds with -ffinite-math-only (llama... |
commit | commitdiff | tree |
| 2024-06-15 |
Radoslav Gerganov | llama : offload to RPC in addition to other backends... |
commit | commitdiff | tree |
| 2024-06-15 |
Masaya, Kato | ggml : use OpenMP as a thread pool (llama/7606) |
commit | commitdiff | tree |
| 2024-06-15 |
0cc4m | Vulkan Mixture of Experts (MoE) support (llama/7628) |
commit | commitdiff | tree |
| next |
overview / pkg / ggml / sources / ggml / shortlog