| Age | Commit message (Expand) | Author |
|---|
| 2024-06-24 | Bitnet: tiny bity faster 1.625 bpw variant on Metal | Iwan Kawrakow |
| 2024-06-22 | bitnet: add 2 bpw quantization | Iwan Kawrakow |
| 2024-06-22 | bitnet: CUDA, scalar, AVX2 | Iwan Kawrakow |
| 2024-06-13 | `build`: rename main → llama-cli, server → llama-server, llava-cli → ll... | Olivier Chafik |
| 2024-06-04 | common : refactor cli arg parsing (#7675) | Georgi Gerganov |
| 2024-05-22 | common : normalize naming style (#7462) | Georgi Gerganov |
| 2024-05-20 | tests : fix --keep_split -> --keep-split (#7374) | Georgi Gerganov |
| 2024-05-19 | quantize : fix --keep-split check (#7374) | Fred Douglas |
| 2024-05-16 | doc: add references to hugging face GGUF-my-repo quantisation web tool. (#7288) | Vaibhav Srivastav |
| 2024-05-08 | ggml : introduce bfloat16 support (#6412) | Justine Tunney |
| 2024-04-26 | quantize: add imatrix and dataset metadata in GGUF (#6658) | Pierrick Hymbert |
| 2024-04-25 | tests : minor bash stuff (#6902) | Georgi Gerganov |
| 2024-04-25 | quantize : add '--keep-split' to quantize model into shards (#6688) | jiez |
| 2024-04-12 | chore: Fix markdown warnings (#6625) | Rene Leonhardt |
| 2024-04-03 | ggml : mul_mat_id use the same tensor for all the experts (#6387) | slaren |
| 2024-03-26 | IQ1_M: 1.75 bpw quantization (#6302) | Kawrakow |
| 2024-03-26 | quantize : be able to override metadata by key (#6321) | Kawrakow |
| 2024-03-22 | quantize: options for output and token embedding tensors qtype (#6239) | Kawrakow |
| 2024-02-27 | IQ4_XS: a 4.25 bpw quantization (#5747) | Kawrakow |
| 2024-02-26 | Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range... | Kawrakow |
| 2024-02-24 | IQ3_S: a much better alternative to Q3_K (#5676) | Kawrakow |
| 2024-02-21 | IQ4_NL: 4-bit non-linear quants with blocks of 32 (#5590) | Kawrakow |
| 2024-02-18 | 1.5 bit quantization (#5453) | Kawrakow |
| 2024-02-16 | ggml : add numa options (#5377) | bmwl |
| 2024-02-03 | refactor : switch to emplace_back to avoid extra object (#5291) | Michael Klimenko |
| 2024-01-30 | SOTA 3-bit quants (#5196) | Kawrakow |
| 2024-01-30 | quantize : fix typo (#5211) | Vladimir Malyutin |
| 2024-01-22 | llama : add Q3_K_XS (#5060) | Kawrakow |
| 2024-01-14 | Add ability to use importance matrix for all k-quants (#4930) | Kawrakow |
| 2024-01-14 | 2-bit quantizations (#4897) | Kawrakow |
| 2024-01-11 | llama : restore intended k-quants mixes for MoE models (#4872) | Kawrakow |
| 2023-11-02 | build : link against build info instead of compiling against it (#3879) | cebtenzzre |
| 2023-10-29 | ggml : quantization refactoring (#3833) | Georgi Gerganov |
| 2023-09-28 | build : enable more non-default compiler warnings (#3200) | Cebtenzzre |
| 2023-09-27 | readme : add some recent perplexity and bpw measurements to READMES, link for... | BarfingLemurs |
| 2023-09-18 | make : restore build-info.h dependency for several targets (#3205) | Cebtenzzre |
| 2023-09-15 | examples : add compiler version and target to build info (#2998) | Cebtenzzre |
| 2023-09-15 | check C++ code with -Wmissing-declarations (#3184) | Cebtenzzre |
| 2023-09-07 | fix some warnings from gcc and clang-tidy (#3038) | Cebtenzzre |
| 2023-09-01 | Allow quantize to only copy tensors, some other improvements (#2931) | Kerfuffle |
| 2023-08-28 | quantize : make output filename optional again (#2823) | Cebtenzzre |
| 2023-08-23 | Fix values shown in the quantize tool help (#2735) | Kawrakow |
| 2023-08-21 | gguf : new file format with flexible meta data (beta) (#2398) | Georgi Gerganov |
| 2023-07-19 | cmake : install targets (#2256) | wzy |
| 2023-07-18 | llama : shorten quantization descriptions | Georgi Gerganov |
| 2023-07-10 | mpi : add support for distributed inference via MPI (#2099) | Evan Miller |
| 2023-06-26 | ggml : add NUMA support (#1556) | zrm |
| 2023-06-13 | Allow "quantizing" to f16 and f32 (#1787) | Kerfuffle |
| 2023-06-10 | llama : support requantizing models instead of only allowing quantization fro... | Kerfuffle |
| 2023-06-05 | ggml : add SOTA 2,3,4,5,6 bit k-quantizations (#1684) | Kawrakow |
