Commit History

Auteur SHA1 Bericht Datum
  Daniel Bevenius d07c621393 common : add llama.vim preset for Qwen2.5 Coder (#11945) 11 maanden geleden
  Georgi Gerganov abd4d0bc4f speculative : update default params (#11954) 11 maanden geleden
  Daniel Bevenius 9626d9351a llama : fix indentation in llama-grammar [no ci] (#11943) 11 maanden geleden
  igardev b58934c183 server : (webui) Enable communication with parent html (if webui is in iframe) (#11940) 11 maanden geleden
  Olivier Chafik 63e489c025 tool-call: refactor common chat / tool-call api (+ tests / fixes) (#11900) 11 maanden geleden
  Xuan-Son Nguyen 63ac128563 server : add TEI API format for /rerank endpoint (#11942) 11 maanden geleden
  MoonRide303 5137da7b8c scripts: corrected encoding when getting chat template (#11866) (#11907) 11 maanden geleden
  xiaobing318 09aaf4f1f5 docs : Fix duplicated file extension in test command (#11935) 11 maanden geleden
  Johannes Gäßler 73e2ed3ce3 CUDA: use async data loading for FlashAttention (#11894) 11 maanden geleden
  Eve f7b1116af1 update release requirements (#11897) 11 maanden geleden
  Antoine Viallon c4d29baf32 server : fix divide-by-zero in metrics reporting (#11915) 11 maanden geleden
  Rémy O 2eea03d86a vulkan: implement several ops relevant for ggml_opt (#11769) 11 maanden geleden
  Xuan-Son Nguyen 0f2bbe6564 server : bump httplib to 0.19.0 (#11908) 11 maanden geleden
  standby24x7 fe163d5bf3 common : Fix a typo in help (#11899) 11 maanden geleden
  Xuan-Son Nguyen 818a340ea8 ci : fix (again) arm64 build fails (#11895) 11 maanden geleden
  Jeff Bolz bf42a23d0a vulkan: support multi/vision rope, and noncontiguous rope (#11902) 11 maanden geleden
  Hale Chan c2ea16f260 metal : fix the crash caused by the lack of residency set support on Intel Macs. (#11904) 11 maanden geleden
  Johannes Gäßler 6dde178248 scripts: fix compare-llama-bench commit hash logic (#11891) 11 maanden geleden
  708-145 fc10c38ded examples: fix typo in imatrix/README.md (#11884) 11 maanden geleden
  Adrian Kretz 22885105a6 metal : optimize dequant q6_K kernel (#11892) 11 maanden geleden
  Georgi Gerganov c2cd24fbfd readme : add notice about new package registry (#11890) 11 maanden geleden
  Georgi Gerganov 68ff663a04 repo : update links to new url (#11886) 11 maanden geleden
  Olivier Chafik f355229692 server: fix type promotion typo causing crashes w/ --jinja w/o tools (#11880) 11 maanden geleden
  Rémy O fc1b0d0936 vulkan: initial support for IQ1_S and IQ1_M quantizations (#11528) 11 maanden geleden
  Michał Moskal 89daa2564f llguidance build fixes for Windows (#11664) 11 maanden geleden
  lhez 300907b211 opencl: Fix rope and softmax (#11833) 11 maanden geleden
  Diego Devesa 94b87f87b5 cuda : add ampere to the list of default architectures (#11870) 11 maanden geleden
  Georgi Gerganov dbc2ec59b5 docker : drop to CUDA 12.4 (#11869) 11 maanden geleden
  Daniel Bevenius 3d68f034da llama : add completion for --chat-template-file (#11860) 11 maanden geleden
  Jinyang He 38e32eb6a0 ggml: optimize some vec dot functions for LoongArch ASX (#11842) 11 maanden geleden