| 2024-01-12 |
Georgi Gerganov | sync : llama.cpp |
commit | commitdiff | tree |
| 2024-01-12 |
slaren | llama : ggml-backend integration (llama/4766) |
commit | commitdiff | tree |
| 2024-01-12 |
Johannes Gäßler | CUDA: fix softmax compile for old CUDA versions (llama... |
commit | commitdiff | tree |
| 2024-01-12 |
Kawrakow | Importance Matrix calculation (llama/4861) |
commit | commitdiff | tree |
| 2024-01-11 |
Georgi Gerganov | sync : whisper.cpp |
commit | commitdiff | tree |
| 2024-01-11 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2024-01-11 |
Georgi Gerganov | main : add cli option to disable system prints (whisper... |
commit | commitdiff | tree |
| 2024-01-11 |
Georgi Gerganov | sync : llama.cpp |
commit | commitdiff | tree |
| 2024-01-11 |
Kawrakow | ggml : SOTA 2-bit quants (add IQ2_XS) (llama/4856) |
commit | commitdiff | tree |
| 2024-01-11 |
Paul Tsochantaris | metal : put encoder debug group behind a define (llama... |
commit | commitdiff | tree |
| 2024-01-11 |
Georgi Gerganov | metal : improve dequantize precision to match CPU ... |
commit | commitdiff | tree |
| 2024-01-11 |
Georgi Gerganov | ggml : fix vld1q_s8_x4 32-bit compat (llama/4828) |
commit | commitdiff | tree |
| 2024-01-11 |
Johannes Gäßler | CUDA: faster softmax via shared memory + fp16 math... |
commit | commitdiff | tree |
| 2024-01-11 |
Georgi Gerganov | metal : fix deprecation warning (#690) |
commit | commitdiff | tree |
| 2024-01-11 |
Timothy Cronin | ggml : remove ggml_cpy_inplace and ggml_cont_inplace... |
commit | commitdiff | tree |
| 2024-01-10 |
otaGran | Update README.md (#692) |
commit | commitdiff | tree |
| 2024-01-10 |
Jack Mousseau | metal : wrap each operation in debug group (#690) |
commit | commitdiff | tree |
| 2024-01-10 |
leejet | ggml : change GGML_MAX_NAME at compile time (#682) |
commit | commitdiff | tree |
| 2024-01-09 |
Halalaluyafail3 | Fix execlp call (#689) |
commit | commitdiff | tree |
| 2024-01-08 |
Georgi Gerganov | sync : llama.cpp |
commit | commitdiff | tree |
| 2024-01-08 |
Kawrakow | SOTA 2-bit quants (llama/4773) |
commit | commitdiff | tree |
| 2024-01-08 |
Johannes Gäßler | CUDA: fixed redundant value dequantization (llama/4809) |
commit | commitdiff | tree |
| 2024-01-08 |
Konstantin... | ggml : use __builtin_amdgcn_sudot4 in __dp4a for gfx11... |
commit | commitdiff | tree |
| 2024-01-08 |
Georgi Gerganov | ggml : do not sched_yield when calling BLAS (llama... |
commit | commitdiff | tree |
| 2024-01-08 |
Johannes Gäßler | Print backend name on test-backend-ops failure (llama... |
commit | commitdiff | tree |
| 2024-01-08 |
Georgi Gerganov | ggml : include stdlib.h before intrin.h (llama/4736) |
commit | commitdiff | tree |
| 2024-01-06 |
旺旺碎冰冰 | fix ROCm on Windows (#683) |
commit | commitdiff | tree |
| 2024-01-05 |
postmasters | gguf : add keys for kv sizes to spec (#676) |
commit | commitdiff | tree |
| 2024-01-05 |
Erik Scholz | fix : cuda order of synchronization when setting a... |
commit | commitdiff | tree |
| 2024-01-05 |
Georgi Gerganov | metal : switch back to default.metallib (#681) |
commit | commitdiff | tree |
| 2024-01-05 |
Georgi Gerganov | ggml : fix q2_k bpw in comments (#680) |
commit | commitdiff | tree |
| 2024-01-04 |
Georgi Gerganov | whisper : reset the "batched" timings (whisper/1721) |
commit | commitdiff | tree |
| 2024-01-04 |
Finn Voorhees | ggml : add error handling to graph_compute (whisper... |
commit | commitdiff | tree |
| 2024-01-03 |
Georgi Gerganov | scripts : allow to skip commits during sync (#678) |
commit | commitdiff | tree |
| 2024-01-03 |
Georgi Gerganov | Update src/ggml-cuda.cu |
commit | commitdiff | tree |
| 2024-01-03 |
Georgi Gerganov | cuda : mark I16 and I32 ops as unsupported |
commit | commitdiff | tree |
| 2024-01-03 |
Georgi Gerganov | metal : add kernel_get_rows_i32 |
commit | commitdiff | tree |
| 2024-01-03 |
Georgi Gerganov | sync : llama.cpp |
commit | commitdiff | tree |
| 2024-01-03 |
Georgi Gerganov | metal : optimize ggml_mul_mat_id (faster Mixtral PP... |
commit | commitdiff | tree |
| 2024-01-03 |
Georgi Gerganov | metal : enable shader debugging (cmake option) (llama... |
commit | commitdiff | tree |
| 2024-01-03 |
Georgi Gerganov | ggml : add ggml_vdotq_s32 alias (llama/4715) |
commit | commitdiff | tree |
| 2024-01-03 |
Johannes Gäßler | CUDA: fixed tensor cores not being used on RDNA3 (llama... |
commit | commitdiff | tree |
| 2024-01-03 |
automaticcat | ggml : add ggml_cpu_has_avx_vnni() (llama/4589) |
commit | commitdiff | tree |
| 2024-01-03 |
Johannes Gäßler | CUDA: fix tensor core logic for Pascal and HIP (llama... |
commit | commitdiff | tree |
| 2024-01-03 |
hydai | cuda: fix vmm oom issue on NVIDIA AGX Orin (llama/4687) |
commit | commitdiff | tree |
| 2024-01-03 |
Georgi Gerganov | scripts : fix sync order + metal sed |
commit | commitdiff | tree |
| 2024-01-03 |
Ashraful Islam | swift : add Swift Package declaration (#674) |
commit | commitdiff | tree |
| 2023-12-29 |
Guillaume Wenzek | ggml : extend ggml_get_rows, ggml_repeat, ggml_concat... |
commit | commitdiff | tree |
| 2023-12-29 |
Georgi Gerganov | scripts : do not sync synced commits |
commit | commitdiff | tree |
| 2023-12-29 |
Georgi Gerganov | sync : whisper.cpp |
commit | commitdiff | tree |
| 2023-12-29 |
Tamotsu Takahashi | ci : build with CLBlast + ggml-opencl use GGML_API... |
commit | commitdiff | tree |
| 2023-12-29 |
Georgi Gerganov | scripts : print list of sync commits |
commit | commitdiff | tree |
| 2023-12-29 |
Georgi Gerganov | scripts : fix format-patch range |
commit | commitdiff | tree |
| 2023-12-29 |
Georgi Gerganov | scripts : do not sync commits from this repo |
commit | commitdiff | tree |
| 2023-12-29 |
Georgi Gerganov | sync : whisper.cpp |
commit | commitdiff | tree |
| 2023-12-29 |
bobqianic | whisper : Replace WHISPER_PRINT_DEBUG with WHISPER_LOG_... |
commit | commitdiff | tree |
| 2023-12-29 |
Georgi Gerganov | scripts : add sync-whisper-am.sh |
commit | commitdiff | tree |
| 2023-12-29 |
bssrdf | ggml : fix some mul mat cases + add tests for src1... |
commit | commitdiff | tree |
| 2023-12-29 |
Astariul | gpt-2 : update README.md (#671) |
commit | commitdiff | tree |
| 2023-12-29 |
Mayank Kumar Pal | readme : add steps for Android compilation and inferenc... |
commit | commitdiff | tree |
| 2023-12-27 |
Georgi Gerganov | scripts : fix sed in sync-llama.am.sh |
commit | commitdiff | tree |
| 2023-12-27 |
Georgi Gerganov | sync : llama.cpp |
commit | commitdiff | tree |
| 2023-12-27 |
Georgi Gerganov | ggml : fix dot product for ARM (llama/4630) |
commit | commitdiff | tree |
| 2023-12-27 |
slaren | cuda : fix vmm pool with multi GPU (llama/4620) |
commit | commitdiff | tree |
| 2023-12-27 |
WillCorticesAI | Update comment for AdamW implementation reference.... |
commit | commitdiff | tree |
| 2023-12-27 |
FantasyGmm | Fix new CUDA10 compilation errors (llama/4635) |
commit | commitdiff | tree |
| 2023-12-27 |
Georgi Gerganov | sync : llama.cpp |
commit | commitdiff | tree |
| 2023-12-27 |
Georgi Gerganov | cmake : update CUDA build to support VMM |
commit | commitdiff | tree |
| 2023-12-27 |
slaren | cuda : improve cuda pool efficiency using virtual memor... |
commit | commitdiff | tree |
| 2023-12-27 |
slaren | fallback to CPU buffer if host buffer alloc fails ... |
commit | commitdiff | tree |
| 2023-12-27 |
Johannes Gäßler | CUDA: fixed row rounding for 0 tensor splits (llama... |
commit | commitdiff | tree |
| 2023-12-27 |
Georgi Gerganov | scripts : fix PR number parsing during sync |
commit | commitdiff | tree |
| 2023-12-24 |
Georgi Gerganov | scripts : improve llama sync patch |
commit | commitdiff | tree |
| 2023-12-23 |
Georgi Gerganov | scripts : sync tests / headers |
commit | commitdiff | tree |
| 2023-12-23 |
Georgi Gerganov | scripts : remove exit |
commit | commitdiff | tree |
| 2023-12-23 |
Georgi Gerganov | scripts : fix PR number sed |
commit | commitdiff | tree |
| 2023-12-23 |
Georgi Gerganov | scripts : add sync-llama-am.sh |
commit | commitdiff | tree |
| 2023-12-22 |
Georgi Gerganov | sync : llama.cpp (ggml_scale, ggml_row_size, ggml_mul_m... |
commit | commitdiff | tree |
| 2023-12-18 |
slaren | cuda : fix synchronization with tensor get/set (#659) |
commit | commitdiff | tree |
| 2023-12-18 |
leejet | cuda : fix im2col_f32_f16 (#658) |
commit | commitdiff | tree |
| 2023-12-14 |
chengchi | cmake : change installation path of static libraries... |
commit | commitdiff | tree |
| 2023-12-13 |
Georgi Gerganov | sync : llama (mul_mat_id + get_rows kernels, typos... |
commit | commitdiff | tree |
| 2023-12-13 |
Steward Garcia | ggml: new gpu kernels + extends ggml_leaky_relu + ggml_... |
commit | commitdiff | tree |
| 2023-12-13 |
ariez-xyz | gguf : document Mixtral changes in spec (#646) |
commit | commitdiff | tree |
| 2023-12-08 |
Georgi Gerganov | sync : whisper.cpp (metal soft max fix + example prints) |
commit | commitdiff | tree |
| 2023-12-07 |
Georgi Gerganov | sync : llama.cpp (fused soft max, gpu cpy ops, etc... |
commit | commitdiff | tree |
| 2023-12-07 |
slaren | ggml-backend : remove backend self-registration (#641) |
commit | commitdiff | tree |
| 2023-12-07 |
slaren | test-backend-ops : add performance eval mode + improve... |
commit | commitdiff | tree |
| 2023-12-05 |
slaren | test-backend-ops : initialize ggml_argsort test with... |
commit | commitdiff | tree |
| 2023-12-05 |
Georgi Gerganov | metal : check supported ops at runtime (#632) |
commit | commitdiff | tree |
| 2023-12-05 |
slaren | ggml : full broadcast in mul, add, div + ggml_mul_mat_i... |
commit | commitdiff | tree |
| 2023-12-05 |
Georgi Gerganov | readme : add link to seamless_comm repo |
commit | commitdiff | tree |
| 2023-12-05 |
Judd | ggml : disable `fprintf` when building with NDEBUG... |
commit | commitdiff | tree |
| 2023-12-01 |
slaren | ggml-cuda : fix usage without CUDA devices (#627) |
commit | commitdiff | tree |
| 2023-12-01 |
RiverZhou | cmake : add ROCm config (#626) |
commit | commitdiff | tree |
| 2023-11-30 |
slaren | ggml-backend update: buffer types, backend registry... |
commit | commitdiff | tree |
| 2023-11-23 |
magicse | tests : update test-vec0.c for mingw (#619) |
commit | commitdiff | tree |
| 2023-11-23 |
Georgi Gerganov | readme : add vit.cpp (#618) |
commit | commitdiff | tree |
| 2023-11-19 |
slaren | gguf : add tokenizer.chat_template documentation (... |
commit | commitdiff | tree |
| 2023-11-17 |
Guillaume Wenzek | ggml : fix ggml_set_2d_inplace (#611) |
commit | commitdiff | tree |
| next |
overview / pkg / ggml / sources / ggml / shortlog