| 2024-03-08 |
Eve | make portability_enumeration_ext apple only (llama... |
commit | commitdiff | tree |
| 2024-03-08 |
leejet | add some new ops, fix some operators and add batch... |
commit | commitdiff | tree |
| 2024-03-06 |
F1L1P | examples : Auto lowercase language parameter in main... |
commit | commitdiff | tree |
| 2024-03-06 |
zhouwg | examples : fix typo in bench.cpp (#1933) |
commit | commitdiff | tree |
| 2024-03-05 |
zhouwg | whisper : fix typo (#1925) |
commit | commitdiff | tree |
| 2024-03-05 |
zhouwg | whisper.android.java : fix returns in JNI (#1929) |
commit | commitdiff | tree |
| 2024-03-04 |
kennethge | cmake : add library versioning (#1352) |
commit | commitdiff | tree |
| 2024-03-04 |
Gavin Cai | readme : recommend MacOS Sonoma for Core ML (#1917) |
commit | commitdiff | tree |
| 2024-02-28 |
Georgi Gerganov | talk-llama : sync llama.cpp |
commit | commitdiff | tree |
| 2024-02-28 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2024-02-28 |
Georgi Gerganov | sync : llama.cpp (ggml/0) |
commit | commitdiff | tree |
| 2024-02-28 |
Kawrakow | ggml : make i-quants work with super-blocks of 64 ... |
commit | commitdiff | tree |
| 2024-02-28 |
Kawrakow | Attempt to fix android build (llama/5752) |
commit | commitdiff | tree |
| 2024-02-28 |
Kawrakow | IQ4_XS: a 4.25 bpw quantization (llama/5747) |
commit | commitdiff | tree |
| 2024-02-28 |
Engininja2 | cuda : replace remaining shfl_xor with calls to warp_re... |
commit | commitdiff | tree |
| 2024-02-28 |
Engininja2 | ggml-quants : fix avx2 iq1_s vec_dot when compiled... |
commit | commitdiff | tree |
| 2024-02-28 |
Kawrakow | Adding IQ2_S and IQ2_M to complete coverage of the... |
commit | commitdiff | tree |
| 2024-02-28 |
Johannes Gäßler | CUDA: fix DEBUG_CUDA_MALLOC (llama/5729) |
commit | commitdiff | tree |
| 2024-02-28 |
AidanBeltonS | Add support for soft_max ALiBi (llama/5639) |
commit | commitdiff | tree |
| 2024-02-28 |
Radosław Gryta | ggml-quants : provide ggml_vqtbl1q_u8 for 64bit compati... |
commit | commitdiff | tree |
| 2024-02-28 |
slaren | add google magika inference example (ggml/748) |
commit | commitdiff | tree |
| 2024-02-26 |
Andrew S | stream.wasm : fix invalid memory access when no segment... |
commit | commitdiff | tree |
| 2024-02-25 |
Georgi Gerganov | talk-llama : sync llama.cpp |
commit | commitdiff | tree |
| 2024-02-25 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2024-02-25 |
Georgi Gerganov | sync : llama.cpp (ggml/0) |
commit | commitdiff | tree |
| 2024-02-25 |
Georgi Gerganov | code : normalize enum names (llama/5697) |
commit | commitdiff | tree |
| 2024-02-25 |
Kawrakow | IQ3_S: a much better alternative to Q3_K (llama/5676) |
commit | commitdiff | tree |
| 2024-02-25 |
UEXTM.com | Introduce backend GUIDs (ggml/743) |
commit | commitdiff | tree |
| 2024-02-24 |
Tamotsu Takahashi | talk, talk-llama : pass text_to_speak as a file (#1865) |
commit | commitdiff | tree |
| 2024-02-23 |
Abhilash Majumder | whisper : add SYCL support (#1863) |
commit | commitdiff | tree |
| 2024-02-22 |
Georgi Gerganov | talk-llama : sync llama.cpp |
commit | commitdiff | tree |
| 2024-02-22 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2024-02-22 |
Georgi Gerganov | ggml : always define ggml_fp16_t as uint16_t (llama... |
commit | commitdiff | tree |
| 2024-02-22 |
Georgi Gerganov | ci : fix whitespace |
commit | commitdiff | tree |
| 2024-02-22 |
Georgi Gerganov | ggml : 32-bit arm compat (#1891) |
commit | commitdiff | tree |
| 2024-02-22 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2024-02-22 |
Georgi Gerganov | sync : llama.cpp (ggml/0) |
commit | commitdiff | tree |
| 2024-02-22 |
Meng, Hengyu | conext add name (llama/5624) |
commit | commitdiff | tree |
| 2024-02-22 |
AidanBeltonS | Update ggml_sycl_op_mul_mat_vec_q (llama/5502) |
commit | commitdiff | tree |
| 2024-02-22 |
0cc4m | Refactor validation and enumeration platform checks... |
commit | commitdiff | tree |
| 2024-02-22 |
0cc4m | Add check for VK_KHR_portability_enumeration for Molten... |
commit | commitdiff | tree |
| 2024-02-22 |
Mathijs de... | Add preprocessor checks for Apple devices. |
commit | commitdiff | tree |
| 2024-02-22 |
Mathijs de... | Resolve ErrorIncompatibleDriver with Vulkan on MacOS. |
commit | commitdiff | tree |
| 2024-02-22 |
Mathijs de... | Allow for Vulkan build with Accelerate. |
commit | commitdiff | tree |
| 2024-02-22 |
slaren | cuda : ignore peer access already enabled errors (llama... |
commit | commitdiff | tree |
| 2024-02-22 |
Siddharth Ramakrishnan | ggml : compute forward no longer pass src tensors ... |
commit | commitdiff | tree |
| 2024-02-22 |
bssrdf | ggml : fix conv_2d batch mode (ggml/737) |
commit | commitdiff | tree |
| 2024-02-22 |
st-gr | openvino : fix convert-whisper-to-openvino.py (#1890) |
commit | commitdiff | tree |
| 2024-02-22 |
Davidson Francis | main : fix file existence check in main.cpp (#1889) |
commit | commitdiff | tree |
| 2024-02-20 |
Georgi Gerganov | talk-llama : sync llama.cpp |
commit | commitdiff | tree |
| 2024-02-20 |
LBlue | make : fix CUBLAS link with WSL (#1878) |
commit | commitdiff | tree |
| 2024-02-19 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2024-02-19 |
Georgi Gerganov | ggml : resolve merge conflicts (ggml/0) |
commit | commitdiff | tree |
| 2024-02-19 |
Georgi Gerganov | common : add IQ1_S (ggml/0) |
commit | commitdiff | tree |
| 2024-02-19 |
Georgi Gerganov | ci : enable -Werror for CUDA builds (llama/5579) |
commit | commitdiff | tree |
| 2024-02-19 |
slaren | cuda, metal : fix nans in soft_max (llama/5574) |
commit | commitdiff | tree |
| 2024-02-19 |
bmwl | ggml : android and old glibc NUMA incompatibility bugfi... |
commit | commitdiff | tree |
| 2024-02-19 |
Georgi Gerganov | ggml : restore vec dot stride arg names (llama/5453) |
commit | commitdiff | tree |
| 2024-02-19 |
Georgi Gerganov | ci : fix wikitext url + compile warnings (llama/5569) |
commit | commitdiff | tree |
| 2024-02-19 |
Georgi Gerganov | metal : fix unused warnings (llama/0) |
commit | commitdiff | tree |
| 2024-02-19 |
Herman Semenov | ggml, common, examples, tests : fixed type arguments... |
commit | commitdiff | tree |
| 2024-02-19 |
Kawrakow | 1.5 bit quantization (llama/5453) |
commit | commitdiff | tree |
| 2024-02-19 |
Georgi Gerganov | ggml : add ALiBi support for ggml_soft_max_ext (llama... |
commit | commitdiff | tree |
| 2024-02-19 |
Ananta Bastola | ci : add an option to fail on compile warning (llama... |
commit | commitdiff | tree |
| 2024-02-19 |
Georgi Gerganov | cmake : fix VULKAN and ROCm builds (llama/5525) |
commit | commitdiff | tree |
| 2024-02-19 |
bmwl | ggml : add numa options (llama/5377) |
commit | commitdiff | tree |
| 2024-02-19 |
slaren | cuda : print message when initialization fails (llama... |
commit | commitdiff | tree |
| 2024-02-19 |
Neuman Vong | vulkan: Find optimal memory type but with fallback... |
commit | commitdiff | tree |
| 2024-02-19 |
AT | Early return for zero size calls to get_tensor. (llama... |
commit | commitdiff | tree |
| 2024-02-19 |
Kawrakow | ggml-quants : fix compiler warnings (shadow variable... |
commit | commitdiff | tree |
| 2024-02-19 |
Abhilash Majumder | ggml-sycl: Replace 3d ops with macro (llama/5458) |
commit | commitdiff | tree |
| 2024-02-19 |
Georgi Gerganov | build : update CBLAS flags + fix unused var warning... |
commit | commitdiff | tree |
| 2024-02-19 |
Davidson Francis | main : check if input files exist before proceeding... |
commit | commitdiff | tree |
| 2024-02-19 |
Felix | examples : clean up common code (#1871) |
commit | commitdiff | tree |
| 2024-02-19 |
Jumper775 | models : fix openvino setup info (#1874) |
commit | commitdiff | tree |
| 2024-02-13 |
Georgi Gerganov | models : add update py requirements |
commit | commitdiff | tree |
| 2024-02-12 |
Georgi Gerganov | swift : package no longer use ggml dependency (#1861) |
commit | commitdiff | tree |
| 2024-02-12 |
Georgi Gerganov | whisper : fix external encoder (#1860) |
commit | commitdiff | tree |
| 2024-02-12 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2024-02-12 |
slaren | ggml-alloc : allocate all leafs as if they were inputs... |
commit | commitdiff | tree |
| 2024-02-12 |
Georgi Gerganov | talk-llama : sync llama.cpp |
commit | commitdiff | tree |
| 2024-02-12 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2024-02-12 |
Georgi Gerganov | ggml-backend : sync remnant |
commit | commitdiff | tree |
| 2024-02-12 |
Johannes Gäßler | CUDA: mul_mat_vec_q tiling, refactor mul mat logic... |
commit | commitdiff | tree |
| 2024-02-12 |
Sergio López | vulkan: only use M-sized matmul on Apple GPUs (llama... |
commit | commitdiff | tree |
| 2024-02-12 |
Georgi Gerganov | ggml : fix compile warnings (unused vars) (llama/4966) |
commit | commitdiff | tree |
| 2024-02-12 |
snadampal | ggml : add mmla kernels for quantized GEMM (llama/4966) |
commit | commitdiff | tree |
| 2024-02-12 |
Ian Bull | metal : use autoreleasepool to avoid memory leaks ... |
commit | commitdiff | tree |
| 2024-02-12 |
slaren | ggml-alloc : v3 (ggml/727) |
commit | commitdiff | tree |
| 2024-02-12 |
dscripka | examples : added audio_ctx argument to main and server... |
commit | commitdiff | tree |
| 2024-02-11 |
Didzis Gosko | metal : option to embed MSL source into compiled binary... |
commit | commitdiff | tree |
| 2024-02-11 |
Georgi Gerganov | examples : initialize context params properly (#1852) |
commit | commitdiff | tree |
| 2024-02-10 |
Georgi Gerganov | talk-llama : sync llama.cpp |
commit | commitdiff | tree |
| 2024-02-10 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2024-02-10 |
Georgi Gerganov | src : relocate new backend sources |
commit | commitdiff | tree |
| 2024-02-10 |
Michael Podvitskiy | ggml : fix `error C2078: too many initializers` for... |
commit | commitdiff | tree |
| 2024-02-10 |
Johannes Gäßler | CUDA: more warps for mmvq on NVIDIA (llama/5394) |
commit | commitdiff | tree |
| 2024-02-10 |
Johannes Gäßler | CUDA: fixed mmvq kernel for bs 2,3,4 and -sm row (llama... |
commit | commitdiff | tree |
| 2024-02-10 |
0cc4m | Basic Vulkan Multi-GPU implementation (llama/5321) |
commit | commitdiff | tree |
| 2024-02-10 |
Johannes Gäßler | CUDA: mul_mat_vec_q max. batch size 8 -> 4 (llama/5370) |
commit | commitdiff | tree |
| next |
overview / pkg / ggml / sources / whisper.cpp / shortlog