Historique des commits

Auteur SHA1 Message Date
  Georgi Gerganov 6cdabe6526 llama-bench : add embeddings option (#5924) il y a 1 an
  Neo Zhang Jianyu 89fb735fcf Revert "[SYCL] fix error when set main gpu to non-zero (#5901)" (#5918) il y a 1 an
  Minsoo Cheong 55a2a900ff server : add `/v1/completions` endpoint (#5914) il y a 1 an
  Georgi Gerganov 2002bc96bf server : refactor (#5882) il y a 1 an
  Neo Zhang Jianyu ceca1aef07 [SYCL] fix error when set main gpu to non-zero (#5901) il y a 1 an
  Jared Van Bortel e04e04f8fa ggml : use SYS_get_cpu if SYS_getcpu is not defined (#5906) il y a 1 an
  bobqianic e25fb4b18f ggml : use `uint8x16_t` return type for `ggml_vqtbl1q_u8` (#5894) il y a 1 an
  Georgi Gerganov 1e35d619a6 convert : remove AWQ remnants (#5768) il y a 1 an
  Neo Zhang Jianyu 8ced9f7e32 add wait() to make code stable (#5895) il y a 1 an
  slaren 652ca2bded compare-llama-bench.py : remove mul_mat_q (#5892) il y a 1 an
  Jared Van Bortel bd836944f8 quants : use MM256_SET_M128I consistently to fix gcc 7 build (#5889) il y a 1 an
  ExtReMLapin 3de31677d3 grammars : blacklists character control set (#5888) il y a 1 an
  Georgi Gerganov 82cb31eb93 Revert "grammars : don't allow to output unescaped new line in string (#5885)" il y a 1 an
  ExtReMLapin b1a4e994fd grammars : don't allow to output unescaped new line in string (#5885) il y a 1 an
  0cc4m 61d1c88e15 Vulkan Improvements (#5835) il y a 1 an
  Neo Zhang Jianyu 21b0867433 [SYCL] fix mul_mat fault in CI/unit-test (#5862) il y a 1 an
  Minsoo Cheong 6a87ac3a52 fix editorconfig check break (#5879) il y a 1 an
  Jeffrey Quesnelle 29eee40474 fix speculative decoding build on windows (#5874) il y a 1 an
  hutli 1d41d6f7c2 nix: static build (#5814) il y a 1 an
  Georgi Gerganov 29ae62d2ae llama : fix embeddings (#5796) il y a 1 an
  Georgi Gerganov e0843afe1b flake : fix il y a 1 an
  Georgi Gerganov a1c6d96ed8 ggml : fix unknown status (#0) il y a 1 an
  Georgi Gerganov efd8533ef8 sync : ggml il y a 1 an
  Michael Podvitskiy 9fa2627347 ggml : introduce ggml_status (ggml/750) il y a 1 an
  Dane Madsen fe52be11e3 cmake : handle cases where git index is not found in .git (#5844) il y a 1 an
  Minsoo Cheong 6d341ab6c5 speculative : implement stochastic speculative sampling (#5625) il y a 1 an
  Xuan Son Nguyen 4ffcdce2ff add alias for chat template (#5858) il y a 1 an
  Georgi Gerganov a0fc62661f sync : ggml il y a 1 an
  leejet 7d43c585dc add some new ops, fix some operators and add batch operations to certain operators. (ggml/747) il y a 1 an
  DAN™ 82f3e668ad common : use LLAMA_DEFAULT_SEED (#5855) il y a 1 an