| Age | Commit message (Expand) | Author |
|---|
| 2023-07-01 | metal : release buffers when freeing metal context (#2062) | Aaron Miller |
| 2023-07-01 | llama : fix return value of llama_load_session_file_internal (#2022) | Georgi Gerganov |
| 2023-07-01 | llama : catch llama_load_session_file_internal exceptions (#2022) | Rand Xie |
| 2023-06-29 | Use unsigned for random seed (#2006) | Howard Su |
| 2023-06-28 | llama : replacing auto &kv with const auto &kv (#2041) | m3ndax |
| 2023-06-28 | llama : remove shards weight file support (#2000) | Howard Su |
| 2023-06-28 | CUDA GPU acceleration for LoRAs + f16 models (#1970) | Johannes Gäßler |
| 2023-06-28 | llama : support input embeddings directly (#1910) | ningshanwutuobang |
| 2023-06-27 | llama : fix rope usage after ChatGLM change | Georgi Gerganov |
| 2023-06-26 | ggml : add NUMA support (#1556) | zrm |
| 2023-06-26 | k-quants : support for super-block size of 64 (#2001) | Kawrakow |
| 2023-06-24 | llama : fix top-p sampling to match the canonical definition (#1953) | Alex Renda |
| 2023-06-24 | llama : make model stateless and context stateful (llama_state) (#1797) | Didzis Gosko |
| 2023-06-20 | llama : fix params struct slignment (#1936) | Ettore Di Giacinto |
| 2023-06-19 | llama : use aligned memory during ggml_init call from loading saved sessions ... | l3utterfly |
| 2023-06-19 | llama : only use Q6_K for output weights if tensor size is multiple of 256 (#... | Kawrakow |
| 2023-06-19 | Convert vector to f16 for dequantize mul mat vec (#1913) | Johannes Gäßler |
| 2023-06-18 | Added tokens per second to info prints (#1928) | Johannes Gäßler |
| 2023-06-18 | Fixed incorrectly applying RMS norm twice (#1925) | Johannes Gäßler |
| 2023-06-18 | llama : prevent usage of k-quants when tensor size is not a multiple of 256 (... | Kawrakow |
| 2023-06-18 | metal : handle buffers larger than device's maxBufferLength (#1826) | Georgi Gerganov |
| 2023-06-17 | llama : fix kv_cache `n` init (close #1903) | Georgi Gerganov |
| 2023-06-17 | ggml : fix warnings under MSVC (#1908) | Howard Su |
| 2023-06-16 | llama : fix embd when offloading non-repeating layers (#1891) | Johannes Gäßler |
| 2023-06-16 | build : fix and ignore MSVC warnings (#1889) | Borislav Stanimirov |
| 2023-06-14 | CUDA full GPU acceleration, KV cache in VRAM (#1827) | Johannes Gäßler |
| 2023-06-13 | train : improved training-from-scratch example (#1652) | xaedes |
| 2023-06-13 | Allow "quantizing" to f16 and f32 (#1787) | Kerfuffle |
| 2023-06-12 | Metal implementation for all k_quants (#1807) | Kawrakow |
| 2023-06-12 | Leverage mmap for offloading tensors to GPU (#1597) | Howard Su |
| 2023-06-10 | llama : support requantizing models instead of only allowing quantization fro... | Kerfuffle |
| 2023-06-09 | OpenCL: Add release memory (#1741) | Robert Sung-wook Shin |
| 2023-06-06 | llama : fix vram_scratch var | Georgi Gerganov |
| 2023-06-06 | llama : fix compile warnings | Georgi Gerganov |
| 2023-06-06 | Multi GPU support, CUDA refactor, CUDA scratch buffer (#1703) | Johannes Gäßler |
| 2023-06-06 | metal : add f16 support | Georgi Gerganov |
| 2023-06-06 | llama : temporary disable Q6_K output quantization (#1711) | Georgi Gerganov |
| 2023-06-06 | metal : add checks for buffer size (#1706) | Spencer Sutton |
| 2023-06-05 | llama : consistently catch and throw only exceptions deriving from std::excep... | mgroeber9110 |
| 2023-06-05 | metal : use shared buffers between CPU and GPU (#1696) | kiltyj |
| 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 | llama : Metal inference (#1642) | Georgi Gerganov |
| 2023-06-04 | OpenCL: Fix duplication of layers in VRAM and RAM, add GPU mul kernel (#1653) | 0cc4m |
| 2023-05-30 | OpenLLaMA 3B support (#1588) | Henri Vasserman |
| 2023-05-23 | OpenCL Token Generation Acceleration (#1459) | 0cc4m |
| 2023-05-20 | llama : define magic numbers as integer constants (#1518) (#1520) | Juuso Alasuutari |
| 2023-05-20 | cuda : loading models directly into VRAM, norm calculation on GPU, broadcasti... | Johannes Gäßler |
| 2023-05-20 | llama : add llama_init_backend() API (close #1527) | Georgi Gerganov |
