| Age | Commit message (Expand) | Author |
|---|
| 2023-10-24 | sync : ggml (conv ops + cuda MSVC fixes) (#3765) | Georgi Gerganov |
| 2023-10-20 | gguf : support big endian platform (#3552) | Qin Yue Chen |
| 2023-10-13 | ggml : add context enumeration functions (#3605) | slaren |
| 2023-10-08 | sync : ggml (ggml-backend) (#3548) | Georgi Gerganov |
| 2023-10-04 | sync : ggml (conv 1d + 2d updates, UB fixes) (#3468) | Georgi Gerganov |
| 2023-09-28 | build : enable more non-default compiler warnings (#3200) | Cebtenzzre |
| 2023-09-28 | ggml_tensor: update the structure comments. (#3283) | Hua Jiang |
| 2023-09-28 | train : finetune LORA (#2632) | xaedes |
| 2023-09-28 | gguf : basic type checking in gguf_get_* (#3346) | Cebtenzzre |
| 2023-09-28 | llama : custom attention mask + parallel decoding + no context swaps (#3228) | Georgi Gerganov |
| 2023-09-27 | metal : reusing llama.cpp logging (#3152) | Rickard Hallerbäck |
| 2023-09-15 | sync : ggml (Metal F32 support + reduce ggml-alloc size) (#3192) | Georgi Gerganov |
| 2023-09-12 | arm64 support for windows (#3007) | Eric Sommerlade |
| 2023-08-29 | ggml : add view_src and view_offs to ggml_tensor for views (#2874) | slaren |
| 2023-08-28 | train : mem usage and other improvements (#2439) | xaedes |
| 2023-08-28 | ggml : sync (mem align to header + conv_transpose_2d fixes + ggml_alloc) (#2852) | Georgi Gerganov |
| 2023-08-27 | gguf : add 64-bit support (GGUF v2) (#2821) | Georgi Gerganov |
| 2023-08-27 | ggml : detect SSSE3 (#2825) | Przemysław Pawełczyk |
| 2023-08-23 | llm : add Falcon support (#2717) | Georgi Gerganov |
| 2023-08-22 | ggml : sync latest (SAM + SD operators, CUDA alibi) (#2709) | Georgi Gerganov |
| 2023-08-22 | ggml : support CUDA's half type for aarch64(#1455) (#2670) | Kylin |
| 2023-08-21 | gguf : new file format with flexible meta data (beta) (#2398) | Georgi Gerganov |
| 2023-08-20 | ggml : move all type info to ggml_type_traits (#2663) | slaren |
| 2023-08-07 | ggml : sync (custom ops) (#2537) | Georgi Gerganov |
| 2023-07-30 | ggml : add graph tensor allocator (#2411) | slaren |
| 2023-07-26 | ggml : allocate graphs in a context (#2392) | slaren |
| 2023-07-25 | ggml : improve graph build time via hash table lookup (#2329) | slaren |
| 2023-07-24 | make rms_norm_eps a parameter (#2374) | slaren |
| 2023-07-24 | ggml : sync (unary ops refactor, static-correctness) (#2370) | Georgi Gerganov |
| 2023-07-23 | ggml: move op parameters from tensors to ggml_tensor::op_params (#2333) | slaren |
| 2023-07-21 | ggml : fix rope args order + assert (#2054) | Georgi Gerganov |
| 2023-07-15 | llama : add custom RoPE (#2054) | Xiao-Yong Jin |
| 2023-07-12 | ggml : add ggml_pool_1d and ggml_pool_2d | Georgi Gerganov |
| 2023-07-11 | ggml : sync (abort callback, mul / add broadcast, fix alibi) (#2183) | Georgi Gerganov |
| 2023-07-11 | ggml : remove src0 and src1 from ggml_tensor and rename opt to src (#2178) | Spencer Sutton |
| 2023-07-07 | ggml : change ggml_graph_compute() API to not require context (#1999) | Qingyou Meng |
| 2023-07-06 | ggml : fix restrict usage | Georgi Gerganov |
| 2023-07-05 | ggml : generalize `quantize_fns` for simpler FP16 handling (#1237) | Stephan Walter |
| 2023-07-04 | ggml : sync latest (new ops, macros, refactoring) (#2106) | Georgi Gerganov |
| 2023-07-01 | ggml : disable GGML_TASK_INIT and GGML_TASK_FINALIZE by default (#1995) | Qingyou Meng |
| 2023-06-27 | ggml : add support for ChatGLM RoPE | Georgi Gerganov |
| 2023-06-26 | ggml : increase max tensor name + clean up compiler warnings in train-text (#... | David Yang |
| 2023-06-26 | ggml : add NUMA support (#1556) | zrm |
| 2023-06-25 | ggml : sync latest ggml (custom operators) | Georgi Gerganov |
| 2023-06-24 | ggml : improve ggml_graph_dump_dot, add ggml_format_name (#1978) | slaren |
| 2023-06-19 | ggml : sync latest ggml repo (#1924) | Georgi Gerganov |
| 2023-06-18 | metal : handle buffers larger than device's maxBufferLength (#1826) | Georgi Gerganov |
| 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 |
| 2023-06-06 | Multi GPU support, CUDA refactor, CUDA scratch buffer (#1703) | Johannes Gäßler |
