Commit History

Auteur SHA1 Bericht Datum
  Aaron Teo def5404f26 common: add LLAMA_LOG_FILE env var (#17609) 1 maand geleden
  ddh0 5a6241feb0 common: update env var name (#17588) 1 maand geleden
  Xuan-Son Nguyen e509411cf1 server: enable jinja by default, update docs (#17524) 1 maand geleden
  Aaron Teo 877566d512 llama: introduce support for model-embedded sampling parameters (#17120) 1 maand geleden
  Georgi Gerganov f914544b16 batched-bench : add "separate text gen" mode (#17103) 2 maanden geleden
  Xuan-Son Nguyen aa3b7a90b4 arg: add --cache-list argument to list cached models (#17073) 2 maanden geleden
  Xuan-Son Nguyen 5c9a18e674 common: move download functions to download.(cpp|h) (#17059) 2 maanden geleden
  Xuan-Son Nguyen 070ff4d535 mtmd: add --image-min/max-tokens (#16921) 2 maanden geleden
  Sigbjørn Skjæret 961660b8c3 common : allow --system-prompt-file for diffusion-cli (#16903) 2 maanden geleden
  Shagun Bera 835e918d84 common: fix typo in cli help text (#16864) 2 maanden geleden
  Sam Malayek 1c1409e131 embedding: add raw option for --embd-output-format (#16541) 2 maanden geleden
  Xuan-Son Nguyen d0660f237a mtmd-cli : allow using --jinja (#16718) 2 maanden geleden
  takasurazeem 6f5d924637 common : Update the docs on -t --threads (#16236) 3 maanden geleden
  Georgi Gerganov 4b2dae383d common : update presets (#16504) 3 maanden geleden
  Georgi Gerganov d00cbea63c server : host-memory prompt caching (#16391) 3 maanden geleden
  Pascal 12bbc3fa50 refactor: centralize CoT parsing in backend for streaming mode (#16394) 3 maanden geleden
  Georgi Gerganov ef4c5b87ea presets : fix pooling param for embedding models (#16455) 3 maanden geleden
  Gadflyii 3df2244df4 llama : add --no-host to disable host buffers (#16310) 3 maanden geleden
  Radoslav Gerganov 898acba681 rpc : add support for multiple devices (#16276) 3 maanden geleden
  ddh0 f6dcda3900 server : context checkpointing for hybrid and recurrent models (#16382) 3 maanden geleden
  Adrien Gallouët 4201deae9c common: introduce http.h for httplib-based client (#16373) 3 maanden geleden
  Adrien Gallouët bf6f3b3a19 common : disable progress bar without a tty (#16352) 3 maanden geleden
  Adrien Gallouët 364a7a6d4a common : remove common_has_curl() (#16351) 3 maanden geleden
  Adrien Gallouët 3c62aed89f common : simplify etag tracking by removing json (#16342) 3 maanden geleden
  Adrien Gallouët b995a10760 common : use cpp-httplib as a cURL alternative for downloads (#16185) 3 maanden geleden
  Adrien Gallouët 37a23c17bd common : enable `--offline` mode without curl support (#16137) 3 maanden geleden
  Haiyue Wang d05affbab7 common : remove unused local variables (#16140) 3 maanden geleden
  Eric Curtin 4ca088b036 Add resumable downloads for llama-server model loading (#15963) 4 maanden geleden
  jacekpoplawski 8ff206097c llama-bench: add --n-cpu-moe support (#15952) 4 maanden geleden
  Aman Gupta 6d758839ff Add LLaDA-7b-MoE diffusion model (#16003) 4 maanden geleden