Commit History

Автор SHA1 Съобщение Дата
  mgroeber9110 5bbe6a9fe9 ggml : portability fixes for VS 2017 (#12150) преди 10 месеца
  Georgi Gerganov afa8a9ec9b llama : add `llama_vocab`, functions -> methods, naming (#11110) преди 1 година
  Georgi Gerganov f66f582927 llama : refactor `src/llama.cpp` (#10902) преди 1 година
  Georgi Gerganov d9d54e498d speculative : refactor and add a simpler example (#10362) преди 1 година
  Xuan Son Nguyen cda0e4b648 llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745) преди 1 година
  Diego Devesa 7eee341bee common : use common_ prefix for common library functions (#9805) преди 1 година
  Georgi Gerganov 6262d13e0b common : reimplement logging (#9418) преди 1 година
  Georgi Gerganov 0abc6a2c25 llama : llama_perf + option to disable timings during decode (#9355) преди 1 година
  Xuan Son Nguyen bfe76d4a17 common : move arg parser code to `arg.cpp` (#9388) преди 1 година
  Xuan Son Nguyen 1b9ae5189c common : refactor arg parser (#9308) преди 1 година
  Georgi Gerganov df270ef745 llama : refactor sampling v2 (#9294) преди 1 година
  Liu Jia 0a4ce78681 common : Changed tuple to struct (TODO fix) (#8823) преди 1 година
  Georgi Gerganov 1442677f92 common : refactor cli arg parsing (#7675) преди 1 година
  Georgi Gerganov 6ff13987ad common : normalize naming style (#7462) преди 1 година
  Pedro Cuenca b97bc3966e llama : support Llama 3 HF conversion (#6745) преди 1 година
  compilade 557410b8f0 llama : greatly reduce output buffer memory usage (#6122) преди 1 година
  compilade c2101a2e90 llama : support Mamba Selective State Space Models (#5328) преди 1 година
  bmwl f486f6e1e5 ggml : add numa options (#5377) преди 1 година
  Georgi Gerganov 6b0a7420d0 llama : KV cache view API + better KV cache management (#4170) преди 2 години
  Daniel Bevenius 9d5949f04b examples : fix typo in parallel example doc comment (#4181) преди 2 години
  cebtenzzre b12fa0d1c1 build : link against build info instead of compiling against it (#3879) преди 2 години
  Marcus Dunn 5be6c803fa llama : remove token functions with `context` args in favor of `model` (#3720) преди 2 години
  Georgi Gerganov d1031cf49c sampling : refactor init to use llama_sampling_params (#3696) преди 2 години
  Georgi Gerganov 0e89203b51 speculative : add tree-based sampling example (#3624) преди 2 години
  Kerfuffle 70c29da118 common : fix mirostat state when using multiple sequences (#3543) преди 2 години
  Georgi Gerganov fcca0a7004 refact : fix convert script + zero out KV cache to avoid nans (#3523) преди 2 години
  pudepiedj a8777ad84e parallel : add option to load external prompt file (#3416) преди 2 години
  Georgi Gerganov ac2219fef3 llama : fix session saving/loading (#3400) преди 2 години
  slaren 16bc66d947 llama.cpp : split llama_context_params into model and context params (#3301) преди 2 години
  Georgi Gerganov ec893798b7 llama : custom attention mask + parallel decoding + no context swaps (#3228) преди 2 години