| 2023-05-19 |
Georgi Gerganov | ggml : use F16 instead of F32 in Q4_0, Q4_1, Q8_0 ... |
commit | commitdiff | tree |
| 2023-05-19 |
Georgi Gerganov | tests : add missing header |
commit | commitdiff | tree |
| 2023-05-19 |
Evan Jones | examples : add persistent chat (#1495) |
commit | commitdiff | tree |
| 2023-05-19 |
Jason McCartney | main : make reverse prompt option act as a stop token... |
commit | commitdiff | tree |
| 2023-05-19 |
David Kennedy | readme : adds WizardLM to the list of supported models... |
commit | commitdiff | tree |
| 2023-05-19 |
Georgi Gerganov | minor : fix compile warnings |
commit | commitdiff | tree |
| 2023-05-18 |
Erik Scholz | make kv_f16 the default for api users (#1517) |
commit | commitdiff | tree |
| 2023-05-18 |
DannyDaemonic | Fixes #1511 lambda issue for w64devkit (mingw) (#1513) |
commit | commitdiff | tree |
| 2023-05-17 |
Stephan Walter | Remove unused n_parts parameter (#1509) |
commit | commitdiff | tree |
| 2023-05-17 |
rankaiyx | benchmark-matmul: Print the average of the test results... |
commit | commitdiff | tree |
| 2023-05-16 |
Tom Jobbins | convert.py: Support models which are stored in a single... |
commit | commitdiff | tree |
| 2023-05-16 |
Ilya Kurdyukov | ~7% faster Q5_1 AVX2 code (#1477) |
commit | commitdiff | tree |
| 2023-05-16 |
András Salamon | define default model path once, sync path with readme... |
commit | commitdiff | tree |
| 2023-05-16 |
sandyiscool | Add alternate include path for openblas (#1476) |
commit | commitdiff | tree |
| 2023-05-15 |
zrm | fix get_num_physical_cores() (#1436) |
commit | commitdiff | tree |
| 2023-05-14 |
slaren | benchmark-matmul: fix clang-tidy issues, report results... |
commit | commitdiff | tree |
| 2023-05-14 |
Johannes Gäßler | cuda : deduplicated dequantization code (#1453) |
commit | commitdiff | tree |
| 2023-05-14 |
xaedes | ggml : alternative fix for race condition bug in non... |
commit | commitdiff | tree |
| 2023-05-14 |
Georgi Gerganov | ggml : various fixes (#1450) |
commit | commitdiff | tree |
| 2023-05-14 |
katsu560 | ggml : add AVX support based on AVX2 code (#1430) |
commit | commitdiff | tree |
| 2023-05-14 |
Georgi Gerganov | ggml : add GGML_QNT_VERSION to track quantization forma... |
commit | commitdiff | tree |
| 2023-05-13 |
Georgi Gerganov | cuda : fix convert function (#1412) |
commit | commitdiff | tree |
| 2023-05-13 |
Georgi Gerganov | make : fix PERF build with cuBLAS |
commit | commitdiff | tree |
| 2023-05-13 |
Georgi Gerganov | llama : fix unused warning |
commit | commitdiff | tree |
| 2023-05-13 |
Georgi Gerganov | ggml : multi-thread mul and diag_mask ops (#1428) |
commit | commitdiff | tree |
| 2023-05-13 |
Johannes Gäßler | ggml : GPU-accelerated token generation (#1412) |
commit | commitdiff | tree |
| 2023-05-13 |
xaedes | ggml : implement backward pass for llama + small traini... |
commit | commitdiff | tree |
| 2023-05-13 |
Georgi Gerganov | ggml : sync alibi fix from ggml repo |
commit | commitdiff | tree |
| 2023-05-13 |
3ooabkhxtn | Adding SSE instructions to ggml_vec_dot_q4_0_q8_0 ... |
commit | commitdiff | tree |
| 2023-05-13 |
Georgi Gerganov | llama : fix various warnings |
commit | commitdiff | tree |
| 2023-05-13 |
Rinne | embedding : remove unused code (#1426) |
commit | commitdiff | tree |
| 2023-05-13 |
Georgi Gerganov | readme : update Q4_0 perplexities |
commit | commitdiff | tree |
| 2023-05-13 |
Georgi Gerganov | llama : free ggml context in set / copy state data... |
commit | commitdiff | tree |
| 2023-05-13 |
Henri Vasserman | opencl : fix kernels for the new formats (#1422) |
commit | commitdiff | tree |
| 2023-05-12 |
Georgi Gerganov | llama : fix --mtest option (close #1414) |
commit | commitdiff | tree |
| 2023-05-12 |
Johannes Gäßler | CLI args use - instead of _, backwards compatible ... |
commit | commitdiff | tree |
| 2023-05-12 |
slaren | Add clang-tidy reviews to CI (#1407) |
commit | commitdiff | tree |
| 2023-05-12 |
Rinne | readme : add C#/.NET bindings repo (#1409) |
commit | commitdiff | tree |
| 2023-05-11 |
Georgi Gerganov | ggml : remove bit shuffling (#1405) |
commit | commitdiff | tree |
| 2023-05-11 |
CRD716 | prompts : model agnostic DAN (#1304) |
commit | commitdiff | tree |
| 2023-05-10 |
Evan Jones | main : add option to save full output to session (... |
commit | commitdiff | tree |
| 2023-05-09 |
DannyDaemonic | Locale fix for Windows (#1379) |
commit | commitdiff | tree |
| 2023-05-09 |
Sami Farin | use pause asm insn in busyloop to run the CPU (13600K... |
commit | commitdiff | tree |
| 2023-05-09 |
DannyDaemonic | Interface improvements and `--multiline-input` (previou... |
commit | commitdiff | tree |
| 2023-05-08 |
Georgi Gerganov | readme : add notice about upcoming breaking change |
commit | commitdiff | tree |
| 2023-05-08 |
AlpinDale | readme : add TOC and Pygmalion instructions (#1359) |
commit | commitdiff | tree |
| 2023-05-08 |
Pavol Rusnak | llama : fix hparams shadow (#1367) |
commit | commitdiff | tree |
| 2023-05-08 |
Georgi Gerganov | llama : require first token to be BOS (#1303) |
commit | commitdiff | tree |
| 2023-05-08 |
ubik2 | convert: add ability to convert safetensors files ... |
commit | commitdiff | tree |
| 2023-05-08 |
Johannes Gäßler | Documented CUDA reproducibility, added warning (#1346) |
commit | commitdiff | tree |
| 2023-05-07 |
Henri Vasserman | CI: add Windows CLBlast and OpenBLAS builds (#1277) |
commit | commitdiff | tree |
| 2023-05-07 |
swittk | ggml : Allow usage of CLBlast alongside Accelerate... |
commit | commitdiff | tree |
| 2023-05-06 |
Jed Fox | Remove default arguments from sampling functions (... |
commit | commitdiff | tree |
| 2023-05-05 |
DaniAndTheWeb | makefile: automatic Arch Linux detection (#1332) |
commit | commitdiff | tree |
| 2023-05-05 |
Erik Scholz | ci : add cublas to windows release (#1271) |
commit | commitdiff | tree |
| 2023-05-05 |
Pavol Rusnak | readme: add missing info (#1324) |
commit | commitdiff | tree |
| 2023-05-05 |
Ionoclast Laboratories | Fix for OpenCL / clbast builds on macOS. (#1329) |
commit | commitdiff | tree |
| 2023-05-05 |
Benjamin Lecaillon | Convert.py @staticmethod (#1327) |
commit | commitdiff | tree |
| 2023-05-04 |
slaren | quantize: make output filename optional, default to... |
commit | commitdiff | tree |
| 2023-05-04 |
Ivan Stepanov | Wrap exceptions in std::exception to verbose output... |
commit | commitdiff | tree |
| 2023-05-04 |
Ivan Stepanov | convert: support DT_BF16 tensors (#1309) |
commit | commitdiff | tree |
| 2023-05-04 |
44670 | readme : add OpenBuddy link (#1321) |
commit | commitdiff | tree |
| 2023-05-04 |
44670 | main : add --in-suffix option (#1318) |
commit | commitdiff | tree |
| 2023-05-04 |
Ron Jailall | ggml : change immintrin.h to intrin.h for compatibility... |
commit | commitdiff | tree |
| 2023-05-04 |
DannyDaemonic | Only escape prompts when used with `-e` (#1311) |
commit | commitdiff | tree |
| 2023-05-04 |
DannyDaemonic | Update main's README.md with new features (#1296) |
commit | commitdiff | tree |
| 2023-05-04 |
Tomas | fix #1224 reverse prompt and multi line (#1297) |
commit | commitdiff | tree |
| 2023-05-03 |
Georgi Gerganov | ggml : vectorize Q8_0 quantization |
commit | commitdiff | tree |
| 2023-05-03 |
khimaros | examples : read chat prompts from a template file ... |
commit | commitdiff | tree |
| 2023-05-03 |
Georgi Gerganov | minor : fix whitespaces (#1302) |
commit | commitdiff | tree |
| 2023-05-03 |
Georgi Gerganov | minor : fix trailing whitespaces |
commit | commitdiff | tree |
| 2023-05-03 |
KASR | scripts : platform independent script to verify sha256... |
commit | commitdiff | tree |
| 2023-05-03 |
CRD716 | examples : various prompt and example fixes (#1298) |
commit | commitdiff | tree |
| 2023-05-03 |
Evan Jones | llama : only copy used KV cache in get / set state... |
commit | commitdiff | tree |
| 2023-05-03 |
DannyDaemonic | Process escape sequences given in prompts (#1173) |
commit | commitdiff | tree |
| 2023-05-03 |
DannyDaemonic | Handle signals properly on Windows (#1123) |
commit | commitdiff | tree |
| 2023-05-03 |
DannyDaemonic | Call sh on build-info.sh (#1294) |
commit | commitdiff | tree |
| 2023-05-03 |
kuvaus | fix build-info.h for git submodules (#1289) |
commit | commitdiff | tree |
| 2023-05-02 |
slaren | fix missing parameters in `llama_init_from_gpt_params... |
commit | commitdiff | tree |
| 2023-05-02 |
Ron Evans | examples : add llama_init_from_gpt_params() common... |
commit | commitdiff | tree |
| 2023-05-02 |
Georgi Gerganov | llama : fix compile warnings |
commit | commitdiff | tree |
| 2023-05-02 |
Georgi Gerganov | ggml : fix 32-bit ARM |
commit | commitdiff | tree |
| 2023-05-02 |
Ron Evans | examples : improve vertical alignment of a few variable... |
commit | commitdiff | tree |
| 2023-05-02 |
Marvin Gießing | ggml : fix ppc64le build error and make cmake detect... |
commit | commitdiff | tree |
| 2023-05-02 |
Robert Brisita | llama : allow 0 as a seed number. (#1275) |
commit | commitdiff | tree |
| 2023-05-02 |
Ron Evans | main : switch input_noecho to input_echo to remove... |
commit | commitdiff | tree |
| 2023-05-02 |
slaren | ggml: add names to tensors (#1268) |
commit | commitdiff | tree |
| 2023-05-01 |
DannyDaemonic | Add git-based build information for better issue tracki... |
commit | commitdiff | tree |
| 2023-05-01 |
slaren | cuBLAS: refactor and optimize f16 mat mul performance... |
commit | commitdiff | tree |
| 2023-05-01 |
xloem | llama : update stubs for systems without mmap and mlock... |
commit | commitdiff | tree |
| 2023-05-01 |
Kerfuffle | ggml : fix ggml_used_mem() (#1264) |
commit | commitdiff | tree |
| 2023-05-01 |
Georgi Gerganov | llama : fix session load / save (#1263) |
commit | commitdiff | tree |
| 2023-05-01 |
slaren | cuBLAS: fall back to pageable memory if pinned alloc... |
commit | commitdiff | tree |
| 2023-05-01 |
Alex Klinkhamer | llama : let context be const when accessing const data... |
commit | commitdiff | tree |
| 2023-04-30 |
Georgi Gerganov | ggml : fix UB (int << 31) |
commit | commitdiff | tree |
| 2023-04-30 |
Pavol Rusnak | build: add armv{6,7,8} support to cmake (#1251) |
commit | commitdiff | tree |
| 2023-04-30 |
jon-chuang | common : better default number of threads (#934) |
commit | commitdiff | tree |
| 2023-04-30 |
0cc4m | ggml : add CLBlast q5_0, q5_1, q8_0 dequant kernels... |
commit | commitdiff | tree |
| 2023-04-30 |
Georgi Gerganov | ggml : add Q5 WASM SIMD + GGML_FTYPE |
commit | commitdiff | tree |
| 2023-04-30 |
Stephan Walter | Various fixes to mat_mul benchmark (#1253) |
commit | commitdiff | tree |
| next |
overview / pkg / ggml / sources / llama.cpp / shortlog