Commit History

Автор SHA1 Съобщение Дата
  Johannes Gäßler a2c199e479 common: clarify instructions for bug reports (#18134) преди 1 месец
  Johannes Gäßler b1f3a6e5db llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653) преди 1 месец
  Georgi Gerganov 254098a279 common : refactor common_sampler + grammar logic changes (#17937) преди 1 месец
  Sigbjørn Skjæret 22577583a3 common : change --color to accept on/off/auto, default to auto (#17827) преди 1 месец
  Adrien Gallouët 83c1171529 common: use native MultiByteToWideChar (#17738) преди 1 месец
  Reese Levine 7ca5991d2b ggml webgpu: add support for emscripten builds (#17184) преди 1 месец
  Xuan-Son Nguyen 13628d8bdb server: add --media-path for local media files (#17697) преди 1 месец
  Xuan-Son Nguyen ec18edfcba server: introduce API for serving / loading / unloading multiple models (#17470) преди 1 месец
  Aaron Teo 877566d512 llama: introduce support for model-embedded sampling parameters (#17120) преди 1 месец
  Georgi Gerganov 196f5083ef common : more accurate sampling timing (#17382) преди 1 месец
  Xuan-Son Nguyen 9b17d74ab7 mtmd: add mtmd_log_set (#17268) преди 2 месеца
  Xuan-Son Nguyen aa3b7a90b4 arg: add --cache-list argument to list cached models (#17073) преди 2 месеца
  Gadflyii 3df2244df4 llama : add --no-host to disable host buffers (#16310) преди 3 месеца
  Aaron Teo 624207e676 devops: add s390x & ppc64le CI (#15925) преди 3 месеца
  Douglas Hanley b5bd037832 llama : add support for qwen3 reranker (#15824) преди 3 месеца
  Uilian Ries 152729f884 common : add missing chrono header for common.cpp (#16211) преди 3 месеца
  Johannes Gäßler e81b8e4b7f llama: use FA + max. GPU layers by default (#15434) преди 4 месеца
  Sigbjørn Skjæret 84ab83cc0b model : jina-embeddings-v3 support (#13693) преди 4 месеца
  Georgi Gerganov 9ebebef62f llama : remove KV cache defragmentation logic (#15473) преди 4 месеца
  Jie Fu (傅杰) 2f3dbffb17 common : fix incorrect print of non-ascii characters in the logging (#15466) преди 4 месеца
  Jonathan Graehl 5cdb27e091 finetune: SGD optimizer, more CLI args (#13873) преди 5 месеца
  Diego Devesa d6818d06a6 llama : allow other bufts when overriding to CPU, add --no-repack option (#14990) преди 5 месеца
  compilade 90083283ec imatrix : use GGUF to store importance matrices (#9400) преди 6 месеца
  Georgi Gerganov 225e7a1438 llama : add high-throughput mode (#14363) преди 6 месеца
  Georgi Gerganov 6ffd4e9c44 server : pre-calculate EOG logit biases (#14721) преди 6 месеца
  Ruikai Peng dd6e6d0b6a vocab : prevent tokenizer overflow (#14301) преди 7 месеца
  fanyang 456af35eb7 build : suppress gcc15 compile warnings (#14261) преди 7 месеца
  Diego Devesa 6adc3c3ebc llama : add thread safety test (#14035) преди 7 месеца
  Georgi Gerganov d3e64b9f49 llama : rework embeddings logic (#14208) преди 7 месеца
  bandoti 2e89f76b7a common: fix issue with regex_escape routine on windows (#14133) преди 7 месеца