| Age | Commit message (Expand) | Author |
|---|
| 2023-09-01 | Allow quantize to only copy tensors, some other improvements (#2931) | Kerfuffle |
| 2023-08-29 | added `struct` to llama_dump_timing_info_yaml's `llama_context` (#2857) | Marcus Dunn |
| 2023-08-28 | YAML result logging + preset script (#2657) | Johannes Gäßler |
| 2023-08-28 | llama.h : add missing struct keyword for C compat in callback type (#2847) | igarnier |
| 2023-08-27 | llama : more tokenizer fixes (#2810) | Georgi Gerganov |
| 2023-08-25 | llama : fix struct decl (#2790) | Marcus Dunn |
| 2023-08-25 | llama : add llama_beam_search() (#2267) | Matt Pulver |
| 2023-08-25 | llama-bench : add model sizes (#2771) | slaren |
| 2023-08-24 | Added `enum` to `llama_token_get_type` return type (#2774) | Marcus Dunn |
| 2023-08-23 | llm : add Falcon support (#2717) | Georgi Gerganov |
| 2023-08-22 | gguf : add ftype meta info to the model (#2710) | Georgi Gerganov |
| 2023-08-21 | gguf : new file format with flexible meta data (beta) (#2398) | Georgi Gerganov |
| 2023-08-18 | llama : add benchmark example (#2626) | slaren |
| 2023-08-14 | llama : add missing enum keyword in function signatures (#2610) | Kamil Tomšík |
| 2023-08-09 | add log_callback to llama_context_params for custom logging. (#2234) | grahameth |
| 2023-07-31 | CUDA: mmq CLI option, fixed mmq build issues (#2453) | Johannes Gäßler |
| 2023-07-25 | Add LLAMA_DEFAULT_RMS_EPS so we can change the default (#2384) | Kawrakow |
| 2023-07-24 | make rms_norm_eps a parameter (#2374) | slaren |
| 2023-07-23 | llama : add grammar-based sampling (#1773) | Evan Jones |
| 2023-07-23 | llama : grouped-query attention + LLaMAv2 70B support (#2276) | Georgi Gerganov |
| 2023-07-21 | llama : remove cfg smooth factor as it is only a reparameterization of the gu... | Guillaume "Vermeille" Sanchez |
| 2023-07-21 | llama : make tensor_split ptr instead of array (#2272) | Georgi Gerganov |
| 2023-07-19 | llama : extend API to get max devices at runtime (#2253) | Rinne |
| 2023-07-15 | llama : add custom RoPE (#2054) | Xiao-Yong Jin |
| 2023-07-14 | llama : add functions that work directly on model (#2197) | Bach Le |
| 2023-07-11 | llama : add classifier-free guidance (#2135) | Bach Le |
| 2023-07-10 | mpi : add support for distributed inference via MPI (#2099) | Evan Miller |
| 2023-07-05 | Expose generation timings from server & update completions.js (#2116) | Tobias Lütke |
| 2023-06-29 | Use unsigned for random seed (#2006) | Howard Su |
| 2023-06-28 | llama : support input embeddings directly (#1910) | ningshanwutuobang |
| 2023-06-26 | ggml : add NUMA support (#1556) | zrm |
| 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 |
| 2023-06-15 | examples : add chat-vicuna.sh (#1854) | yangli2 |
| 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 |
| 2023-06-10 | llama : support requantizing models instead of only allowing quantization fro... | Kerfuffle |
| 2023-06-06 | Multi GPU support, CUDA refactor, CUDA scratch buffer (#1703) | Johannes Gäßler |
| 2023-06-05 | ggml : add SOTA 2,3,4,5,6 bit k-quantizations (#1684) | Kawrakow |
| 2023-06-04 | llama : Metal inference (#1642) | Georgi Gerganov |
| 2023-05-28 | Only show -ngl option when relevant + other doc/arg handling updates (#1625) | Kerfuffle |
| 2023-05-20 | llama : define magic numbers as integer constants (#1518) (#1520) | Juuso Alasuutari |
| 2023-05-20 | llama : add llama_init_backend() API (close #1527) | Georgi Gerganov |
| 2023-05-20 | llama : fix compile warnings in llama_set_state_data() | Georgi Gerganov |
| 2023-05-19 | ggml : use F16 instead of F32 in Q4_0, Q4_1, Q8_0 (#1508) | Georgi Gerganov |
| 2023-05-17 | Remove unused n_parts parameter (#1509) | Stephan Walter |
| 2023-05-13 | ggml : GPU-accelerated token generation (#1412) | Johannes Gäßler |
| 2023-05-13 | llama : free ggml context in set / copy state data (close #1425) | Georgi Gerganov |
| 2023-05-12 | ggml : remove bit shuffling (#1405) | Georgi Gerganov |
| 2023-05-06 | Remove default arguments from sampling functions (#1343) | Jed Fox |
