Commit History

Author SHA1 Message Date
  AlpinDale 2242aabaf4 fix: outlines import errors 1 month ago
  AlpinDale d2971a6831 ci: bump version to 0.6.4 (#845) 1 month ago
  AlpinDale 538471f76e chore: bump mistral_common to 1.5.0 (#844) 1 month ago
  AlpinDale 483c9e6e59 fix: disable awq_marlin override for awq models (#843) 1 month ago
  AlpinDale dfa34d1b24 feat: add sampler_priorty (#837) 1 month ago
  AlpinDale 93bc863591 feat: Machete Kernels for Hopper GPUs (#842) 1 month ago
  AlpinDale 563e8f7ac8 fix: latency and serving benchmarks (#841) 1 month ago
  AlpinDale 7c7ec12f36 chore: refactor executor classes for easier inheritance (#840) 1 month ago
  AlpinDale 16b587c104 fix: hidden states handling in batch expansion for spec decoding (#839) 1 month ago
  AlpinDale 60f7b828d5 feat: add skew sampling (#834) 2 months ago
  AlpinDale ba9d8f631a feat: add no_repeat_ngram sampler (#832) 2 months ago
  Selali 4c4a365f77 feat: Add DRY (Don't Repeat Yourself) sampling (#827) 2 months ago
  AlpinDale 48a8693aed feat: multi-step scheduling (#831) 2 months ago
  AlpinDale 2242cb25dc fix: unbound tokenizer error 2 months ago
  AlpinDale 3d83e64f8e feat: add metrics for prefix cache hit rate (#829) 2 months ago
  AlpinDale 22425b689d fix: XPU build 2 months ago
  AlpinDale bfc8988116 feat: add cuda sampling kernels for top_k and top_p (#828) 2 months ago
  AlpinDale 22427602eb feat: add top-nsigma sampling method 2 months ago
  AlpinDale 22429e4a10 fix: sampler test with new transformers version 2 months ago
  AlpinDale 2f61644f6e SPMD optimizations (#824) 2 months ago
  AlpinDale 32a37e8107 tests: partially fix tensorizer and logprobs tests 2 months ago
  AlpinDale 7f1c9af5e2 fix: fp8 quant test 2 months ago
  AlpinDale 173ac23399 fix: experts int8 quant test 2 months ago
  AlpinDale 68f050129d fix: lora worker manager test import 2 months ago
  AlpinDale 3661de812d fix: lora layer test 2 months ago
  AlpinDale 0a369f9171 feat: support chunked prefill with LoRA (#823) 2 months ago
  AlpinDale e5b1afe625 feat: add chat method for LLM class (#822) 2 months ago
  AlpinDale 262cbc63b7 fix: vision api test template path 2 months ago
  AlpinDale b0113a1eaa fix: tokenization api test (#821) 2 months ago
  AlpinDale c6c91edab7 ci: update & overhaul test units (#769) 2 months ago