Commit History

Автор SHA1 Съобщение Дата
  Sigbjørn Skjæret e562b9714b common : change --no-penalize-nl to --penalize-nl (#6334) преди 1 година
  slaren 280345968d cuda : rename build flag to LLAMA_CUDA (#6299) преди 1 година
  Minsoo Cheong 64e7b47c69 examples : add "retrieval" (#6193) преди 1 година
  Pierrick Hymbert f482bb2e49 common: llama_load_model_from_url split support (#6192) преди 1 година
  Johannes Gäßler 50ccaf5eac lookup: complement data from context with general text statistics (#5479) преди 1 година
  Georgi Gerganov 56a00f0a2f common : default --hf-file to --model (#6234) преди 1 година
  Georgi Gerganov 80bd33bc2c common : add HF arg helpers (#6234) преди 1 година
  Georgi Gerganov 95d576b48e metal : pad n_ctx by 32 (#6177) преди 1 година
  DAN™ fa046eafbc Fix params underscore convert to dash. (#6203) преди 1 година
  Kawrakow 76aa30a263 Add ability to use Q5_0, Q5_1, and IQ4_NL for quantized K cache (#6183) преди 1 година
  DAN™ 4c28b82529 common : print usage on '-h' and '--help' (#6145) преди 1 година
  DAN™ 496bc79bc2 common : tidy-up argument parsing (#6105) преди 1 година
  Pierrick Hymbert d01b3c4c32 common: llama_load_model_from_url using --model-url (#6098) преди 1 година
  DAN™ 15961ec04d common : refactor nested if causing error C1061 on MSVC (#6101) преди 1 година
  Theia Vogel 877b4d0c62 llama : add support for control vectors (#5970) преди 1 година
  Georgi Gerganov 0fd6c1f015 embedding : print cosine similarity (#899) преди 1 година
  slaren f30ea47a87 llama : add pipeline parallelism support (#6017) преди 1 година
  Georgi Gerganov 05b06210c9 llama : more consistent names of count variables (#5994) преди 1 година
  SeungWon Jeong fb215c3832 server : normalize embeddings (#5956) преди 1 година
  compilade c2101a2e90 llama : support Mamba Selective State Space Models (#5328) преди 1 година
  Georgi Gerganov 29ae62d2ae llama : fix embeddings (#5796) преди 1 година
  Minsoo Cheong 6d341ab6c5 speculative : implement stochastic speculative sampling (#5625) преди 1 година
  Douglas Hanley 475df1d6cf llama : allow for user specified embedding pooling type (#5849) преди 1 година
  Neo Zhang Jianyu 715641391d Support multiple GPUs (split mode) on SYCL backend (#5806) преди 1 година
  Miwa / Ensan f49a535686 common : fix flag `--logits-all` to `--all-logits` (#5805) преди 1 година
  Pierrick Hymbert 3ab8b3a92e llama : cleanup unused mmq flags (#5772) преди 1 година
  Georgi Gerganov 9d533a77d0 llama : fix defrag bugs + add parameter (#5735) преди 1 година
  Georgi Gerganov ab336a9d5e code : normalize enum names (#5697) преди 1 година
  Robey Holderith 5ee99c32f5 common, server : surface min_keep as its own parameter (#5567) преди 1 година
  Georgi Gerganov 1dcc3fde00 common : fix ub (#5530) преди 1 година