| Age | Commit message (Expand) | Author |
|---|
| 2023-06-05 | ggml : add SOTA 2,3,4,5,6 bit k-quantizations (#1684) | Kawrakow |
| 2023-06-05 | Increase 3B scratch buffers. (#1698) | Henri Vasserman |
| 2023-06-05 | llama : fix Metal KV cache sync (close #1695) | Georgi Gerganov |
| 2023-06-04 | readme : update hot topics | Georgi Gerganov |
| 2023-06-04 | llama : Metal inference (#1642) | Georgi Gerganov |
| 2023-06-04 | OpenCL: Fix duplication of layers in VRAM and RAM, add GPU mul kernel (#1653) | 0cc4m |
| 2023-06-03 | Add info about CUDA_VISIBLE_DEVICES (#1682) | Henri Vasserman |
| 2023-06-03 | Docker: change to calling convert.py (#1641) | Jiří Podivín |
| 2023-06-03 | Fix prompt cache saving and chat-persistent rollover (#1678) | Evan Jones |
| 2023-05-30 | OpenLLaMA 3B support (#1588) | Henri Vasserman |
| 2023-05-29 | ggml : sync cgraph import / export API | Georgi Gerganov |
| 2023-05-29 | ggml : fix bug in ggml_alibi | Georgi Gerganov |
| 2023-05-29 | Work around for recalculating logits in cached prompts (Fixes #1585) (#1609) | DannyDaemonic |
| 2023-05-28 | Adding git in container package dependencies (#1621) | Jiří Podivín |
| 2023-05-28 | LLAMA_DEBUG adds debug symbols (#1617) | Johannes Gäßler |
| 2023-05-28 | Only show -ngl option when relevant + other doc/arg handling updates (#1625) | Kerfuffle |
| 2023-05-28 | examples : add --alias option to gpt_params to set use friendly model name (#... | Vladimir Zorin |
| 2023-05-28 | opencl : no need to allocate cl_mem on heap (#1612) | Howard Su |
| 2023-05-28 | opencl : use strstr to check if fp16 supported (#1611) | Howard Su |
| 2023-05-27 | ggml : add support for the RISCV architecture (#1616) | apcameron |
| 2023-05-27 | Include server in releases + other build system cleanups (#1610) | Kerfuffle |
| 2023-05-27 | Add documentation about CLBlast (#1604) | Henri Vasserman |
| 2023-05-27 | [CI] Fix openblas (#1613) | Henri Vasserman |
| 2023-05-27 | ggml : add ggml_tensor_overhead() | Georgi Gerganov |
| 2023-05-27 | [CI] CLBlast: Fix directory name (#1606) | Henri Vasserman |
| 2023-05-27 | ggml : sync ggml core (minor additions, e.g. ggml_get_tensor_by_name()) | Georgi Gerganov |
| 2023-05-25 | Some improvements to loading the session with --prompt-cache (#1550) | Kerfuffle |
| 2023-05-26 | cuda : performance optimizations (#1530) | Johannes Gäßler |
| 2023-05-24 | Update CLBlast to 1.6.0 (#1580) | Henri Vasserman |
| 2023-05-24 | readme : add docs for chat-persistent.sh (#1568) | Evan Jones |
| 2023-05-24 | chat-persistent.sh : use bracket expressions in grep (#1564) | Senemu |
| 2023-05-23 | Fix handling of "invalid property" when creating OpenCL command queue (#1565) | Maarten ter Huurne |
| 2023-05-23 | OpenCL Token Generation Acceleration (#1459) | 0cc4m |
| 2023-05-21 | examples : add server example with REST API (#1443) | Steward Garcia |
| 2023-05-21 | make : .PHONY clean (#1553) | Stefan Sydow |
| 2023-05-21 | ggml : output 3d sizes in ggml_graph_dump_dot() | Georgi Gerganov |
| 2023-05-20 | ggml : update WASM SIMD | Georgi Gerganov |
| 2023-05-20 | feature : support blis and other blas implementation (#1536) | Zenix |
| 2023-05-20 | OpenCL: Fixes for older devices. (#1435) | Henri Vasserman |
| 2023-05-20 | llama : define magic numbers as integer constants (#1518) (#1520) | Juuso Alasuutari |
| 2023-05-20 | ggml : add ggml_clamp() (#1539) | Georgi Gerganov |
| 2023-05-20 | cuda : loading models directly into VRAM, norm calculation on GPU, broadcasti... | Johannes Gäßler |
| 2023-05-20 | Revert "feature : add blis and other BLAS implementation support (#1502)" | Georgi Gerganov |
| 2023-05-20 | feature : add blis and other BLAS implementation support (#1502) | Zenix |
| 2023-05-20 | llama : add llama_init_backend() API (close #1527) | Georgi Gerganov |
| 2023-05-20 | Fix for mingw (#1462) | DannyDaemonic |
| 2023-05-20 | llama : fix name shadowing and C4146 (#1526) | Maxime |
| 2023-05-20 | llama : fix compile warnings in llama_set_state_data() | Georgi Gerganov |
| 2023-05-20 | ggml : fix scalar implementation of Q4_1 dot | Georgi Gerganov |
| 2023-05-19 | ggml : use F16 instead of F32 in Q4_0, Q4_1, Q8_0 (#1508) | Georgi Gerganov |
