| 2024-04-14 |
David Renshaw | llama : add missing kv clear in llama_beam_search ... |
commit | commitdiff | tree |
| 2024-04-14 |
Chao Jiang | Add Command R chat template (#6650) |
commit | commitdiff | tree |
| 2024-04-14 |
Georgi Gerganov | flake.lock: Update (#6669) |
commit | commitdiff | tree |
| 2024-04-14 |
Dave | Added support for GGML_OP_CLAMP in Metal (#6662) |
commit | commitdiff | tree |
| 2024-04-14 |
Sigbjørn Skjæret | Fix --split-max-size (#6655) |
commit | commitdiff | tree |
| 2024-04-14 |
Jaemin Son | [bug fix] convert github repository_owner to lowercase... |
commit | commitdiff | tree |
| 2024-04-14 |
James A Capozzoli | convert : enable the `--use-temp-file` cli flag (#6645) |
commit | commitdiff | tree |
| 2024-04-14 |
Neo Zhang Jianyu | fix memcpy() crash, add missed cmd in guide, fix softma... |
commit | commitdiff | tree |
| 2024-04-13 |
Johannes Gäßler | CUDA: fix matrix multiplication logic for tests (#6667) |
commit | commitdiff | tree |
| 2024-04-13 |
Pierrick Hymbert | model: support arch `DbrxForCausalLM` (#6515) |
commit | commitdiff | tree |
| 2024-04-12 |
Olivier Chafik | JSON schema conversion: ⚡️ faster repetitions, min... |
commit | commitdiff | tree |
| 2024-04-12 |
slaren | metal : unify mul_mv_id kernels (#6556) |
commit | commitdiff | tree |
| 2024-04-12 |
Daniel Bevenius | infill : add download instructions for model (#6626) |
commit | commitdiff | tree |
| 2024-04-12 |
Pierrick Hymbert | server : coherent log output for KV cache full (#6637) |
commit | commitdiff | tree |
| 2024-04-12 |
jiez | llama : add gguf_remove_key + remove split meta during... |
commit | commitdiff | tree |
| 2024-04-12 |
Rene Leonhardt | chore: Fix markdown warnings (#6625) |
commit | commitdiff | tree |
| 2024-04-12 |
Georgi Gerganov | imatrix : remove invalid assert (#6632) |
commit | commitdiff | tree |
| 2024-04-12 |
MasterYi1024 | Correct free memory and total memory. (#6630) |
commit | commitdiff | tree |
| 2024-04-12 |
Pierrick Hymbert | eval-callback: use ggml_op_desc to pretty print unary... |
commit | commitdiff | tree |
| 2024-04-12 |
Georgi Gerganov | ci : disable Metal for macOS-latest-cmake-x64 (#6628) |
commit | commitdiff | tree |
| 2024-04-12 |
Clint Herron | Optimization: eliminate addition of redundant stacks... |
commit | commitdiff | tree |
| 2024-04-11 |
Clint Herron | As suggested by @slaren, disabling Metal for test to... |
commit | commitdiff | tree |
| 2024-04-11 |
Nikolas | Refactor Error Handling for CUDA (#6575) |
commit | commitdiff | tree |
| 2024-04-11 |
Olivier Chafik | grammars: 1.5x faster inference w/ complex grammars... |
commit | commitdiff | tree |
| 2024-04-11 |
Hugo Roussel | ci: download artifacts to release directory (#6612) |
commit | commitdiff | tree |
| 2024-04-11 |
Daniel Bevenius | scripts : add --outdir option to hf.sh (#6600) |
commit | commitdiff | tree |
| 2024-04-11 |
Pierrick Hymbert | eval-callback: Example how to use eval callback for... |
commit | commitdiff | tree |
| 2024-04-10 |
Daniel Bevenius | gguf : add option to not check tensor data (#6582) |
commit | commitdiff | tree |
| 2024-04-10 |
Ralph Soika | minor layout improvements (#6572) |
commit | commitdiff | tree |
| 2024-04-10 |
slaren | llama : add model types for mixtral (#6589) |
commit | commitdiff | tree |
| 2024-04-10 |
slaren | convert.py : add consolidated.safetensors for mixtral... |
commit | commitdiff | tree |
| 2024-04-10 |
Pierrick Hymbert | docs : how to add a model (#6565) |
commit | commitdiff | tree |
| 2024-04-10 |
Artem Zinnatullin | readme : fix ROCm link (#6579) |
commit | commitdiff | tree |
| 2024-04-10 |
sjxx | readme : update UI list (#6560) |
commit | commitdiff | tree |
| 2024-04-09 |
Jiří Sejkora | readme: fix typo in amdgpu target name (#6573) |
commit | commitdiff | tree |
| 2024-04-09 |
Jared Van Bortel | BERT tokenizer fixes (#6498) |
commit | commitdiff | tree |
| 2024-04-09 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2024-04-09 |
Ed Lee | server : detect search query to start webchat (#6554) |
commit | commitdiff | tree |
| 2024-04-09 |
Carolinabanana | llama : add Command R Plus support (#6491) |
commit | commitdiff | tree |
| 2024-04-09 |
Georgi Gerganov | license : update copyright notice + add AUTHORS (#6405) |
commit | commitdiff | tree |
| 2024-04-08 |
Georgi Gerganov | llama : fix attention layer count sanity check (#6550) |
commit | commitdiff | tree |
| 2024-04-08 |
kunnis | Comment explaining a decision (#6531) |
commit | commitdiff | tree |
| 2024-04-08 |
Georgi Gerganov | quantize : fix precedence of cli args (#6541) |
commit | commitdiff | tree |
| 2024-04-08 |
Rick G | llama : support negative ith in llama_get_ API (#6519) |
commit | commitdiff | tree |
| 2024-04-08 |
Jan Boon | llama : save and restore kv cache for single seq id... |
commit | commitdiff | tree |
| 2024-04-08 |
Abhilash Majumder | remove row=1 cond (#6532) |
commit | commitdiff | tree |
| 2024-04-08 |
Firat | Adding KodiBot to UI list (#6535) |
commit | commitdiff | tree |
| 2024-04-07 |
Mark Fairbairn | Change Windows AMD example to release build to make... |
commit | commitdiff | tree |
| 2024-04-07 |
Georgi Gerganov | flake.lock: Update (#6517) |
commit | commitdiff | tree |
| 2024-04-07 |
DAN™ | Add GritLM as supported models. (#6513) |
commit | commitdiff | tree |
| 2024-04-07 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2024-04-07 |
Slava Primenko | ggml: bypass code incompatible with CUDA < 11.1 (whispe... |
commit | commitdiff | tree |
| 2024-04-07 |
Georgi Gerganov | scripts : sync ggml-cuda folder |
commit | commitdiff | tree |
| 2024-04-07 |
limitedAtonement | Run make to build the project (#6457) |
commit | commitdiff | tree |
| 2024-04-07 |
Neo Zhang Jianyu | support/fix OPs GGML_TYPE_IQ4_NL, GGML_TYPE_IQ4_XS... |
commit | commitdiff | tree |
| 2024-04-06 |
Georgi Gerganov | sync : ggml |
commit | commitdiff | tree |
| 2024-04-06 |
Daniel Bevenius | backend : fix typo in scheduler documentation (ggml... |
commit | commitdiff | tree |
| 2024-04-06 |
Clint Herron | Tests: Added integration tests for GBNF parser (#6472) |
commit | commitdiff | tree |
| 2024-04-06 |
Pierrick Hymbert | ci: bench: support sse and fix prompt processing time... |
commit | commitdiff | tree |
| 2024-04-05 |
Brian | gguf.py : add licence and version to gguf writer (... |
commit | commitdiff | tree |
| 2024-04-05 |
Hoang Nguyen | readme : update UI list (#6503) |
commit | commitdiff | tree |
| 2024-04-05 |
Ting Sun | bench : make n_batch and n_ubatch configurable in Batch... |
commit | commitdiff | tree |
| 2024-04-05 |
Ouadie EL FAROUKI | [SYCL] Fixed minor bug when enabling FP16 for non intel... |
commit | commitdiff | tree |
| 2024-04-04 |
alexpinel | readme : add Dot to UI list (#6487) |
commit | commitdiff | tree |
| 2024-04-04 |
Jun Jie | readme : fix typo (#6481) |
commit | commitdiff | tree |
| 2024-04-04 |
Ed Lepedus | server: add cURL support to server Dockerfiles (#6474) |
commit | commitdiff | tree |
| 2024-04-04 |
Minsoo Cheong | ci: exempt master branch workflows from getting cancell... |
commit | commitdiff | tree |
| 2024-04-04 |
Ewout ter Hoeven | build CI: Name artifacts (#6482) |
commit | commitdiff | tree |
| 2024-04-04 |
Shakhar Dasgupta | server: allow penalizing repetition of newlines on... |
commit | commitdiff | tree |
| 2024-04-04 |
Pierrick Hymbert | ci: bench fix concurrency for workflow trigger dispatch... |
commit | commitdiff | tree |
| 2024-04-04 |
limitedAtonement | Correct README link (#6458) |
commit | commitdiff | tree |
| 2024-04-04 |
Pierrick Hymbert | ci: bench: add more ftype, fix triggers and bot comment... |
commit | commitdiff | tree |
| 2024-04-04 |
Daniel Bevenius | common: remove duplicate check for curl (#6471) |
commit | commitdiff | tree |
| 2024-04-04 |
Clint Herron | examples : add GBNF validator program (#5948) |
commit | commitdiff | tree |
| 2024-04-04 |
Georgi Gerganov | server : remove obsolete --memory-f32 option |
commit | commitdiff | tree |
| 2024-04-04 |
Xiao-Yong Jin | server : add option to disable KV offload (#6468) |
commit | commitdiff | tree |
| 2024-04-04 |
Clint Herron | convert : fix for lint error complaining of bare except... |
commit | commitdiff | tree |
| 2024-04-03 |
Fattire | A few small fixes to server's README docs (#6428) |
commit | commitdiff | tree |
| 2024-04-03 |
JH23X | server : handle exception on wrong type in request... |
commit | commitdiff | tree |
| 2024-04-03 |
bryanSwk | llama : add SEA-LION support (#6448) |
commit | commitdiff | tree |
| 2024-04-03 |
Ewout ter Hoeven | ci : update checkout, setup-python and upload-artifact... |
commit | commitdiff | tree |
| 2024-04-03 |
Ed Lepedus | server: add cURL support to `server.Dockerfile` (#6461) |
commit | commitdiff | tree |
| 2024-04-03 |
Francisco Melo | readme : add feature-rich rust bindings (#6465) |
commit | commitdiff | tree |
| 2024-04-03 |
Joyce | security : create policy (#6354) |
commit | commitdiff | tree |
| 2024-04-03 |
Abhishek Gopinath K | Missing tokenizer.model error during gguf conversion... |
commit | commitdiff | tree |
| 2024-04-03 |
kaizau | Add OpenChat, Alpaca, Vicuna chat templates (#6397) |
commit | commitdiff | tree |
| 2024-04-03 |
Georgi Gerganov | readme : update hot topics |
commit | commitdiff | tree |
| 2024-04-03 |
slaren | ggml : mul_mat_id use the same tensor for all the exper... |
commit | commitdiff | tree |
| 2024-04-03 |
Meng, Hengyu | [SYCL] Disable iqx on windows as WA (#6435) |
commit | commitdiff | tree |
| 2024-04-01 |
Georgi Gerganov | flake.lock: Update (#6402) |
commit | commitdiff | tree |
| 2024-04-01 |
Johannes Gäßler | compare-llama-bench.py: fix long hexsha args (#6424) |
commit | commitdiff | tree |
| 2024-04-01 |
Pierrick Hymbert | ci: server: verify deps are coherent with the commit... |
commit | commitdiff | tree |
| 2024-03-31 |
Georgi Gerganov | readme : update hot topics |
commit | commitdiff | tree |
| 2024-03-30 |
Pierrick Hymbert | ci: bench: fix Resource not accessible by integration... |
commit | commitdiff | tree |
| 2024-03-29 |
Mohammadreza... | Fedora build update (#6388) |
commit | commitdiff | tree |
| 2024-03-29 |
Xuan Son Nguyen | split: allow --split-max-size option (#6343) |
commit | commitdiff | tree |
| 2024-03-29 |
0cc4m | Vulkan k-quant mmq and ggml-backend offload functionali... |
commit | commitdiff | tree |
| 2024-03-29 |
Georgi Gerganov | sync : ggml (#6351) |
commit | commitdiff | tree |
| 2024-03-29 |
hxer7963 | [Model] Add support for xverse (#6301) |
commit | commitdiff | tree |
| 2024-03-29 |
Georgi Gerganov | ci : fix BGE wget (#6383) |
commit | commitdiff | tree |
| next |
overview / pkg / ggml / sources / llama.cpp / shortlog