1
0

Коммит түүх

Эзэн SHA1 Мессеж Огноо
  AlpinDale b029a544ff optimize eager mode host time with numpy 7 сар өмнө
  AlpinDale f2b7a42c4e fix: async cancels in merge_async_iterators for python>=3.9 7 сар өмнө
  AlpinDale 7194047318 remove vllm-nccl 7 сар өмнө
  AlpinDale 90ceab32ff refactor: consolidate prompt args to LLM engines 7 сар өмнө
  AlpinDale 656459fd84 make fp8_e4m3 work on nvidia 8 сар өмнө
  AlpinDale 251568470e initial nvidia fp8 e4m3 for kv cache 8 сар өмнө
  AlpinDale 4476d2d885 remove cuda version check 8 сар өмнө
  AlpinDale 2351a0e2cd feat: FlashInfer backend for decoding phase (#548) 8 сар өмнө
  AlpinDale 2656df543b why was this removed? weird 8 сар өмнө
  AlpinDale 2e0b115ce1 move func tracing to utils 9 сар өмнө
  AlpinDale 46159b107a formatting: pt1 9 сар өмнө
  AlpinDale fca911ee0a vLLM Upstream Sync (#526) 9 сар өмнө
  AlpinDale f894f7b176 Revert "reduce dedupe by wrapping in general worker class" 10 сар өмнө
  AlpinDale 9fff6fb507 reduce dedupe by wrapping in general worker class 10 сар өмнө
  AlpinDale 9d81716bfd [v0.5.3] Release Candidate (#388) 10 сар өмнө
  AlpinDale e3252edd07 fix: remove event and stream, add typing (#382) 11 сар өмнө
  AlpinDale 33b3786175 fix: cache neuron checks (#379) 1 жил өмнө
  AlpinDale f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) 1 жил өмнө
  AlpinDale e53842bd5d fix: cuda home detection for fp8 kv cache 1 жил өмнө
  AlpinDale e42a78381a feat: switch from pylint to ruff (#322) 1 жил өмнө
  AlpinDale c2d77b1822 chore: logging refactor (#302) 1 жил өмнө
  AlpinDale 9810daa699 feat: INT8 KV Cache (#298) 1 жил өмнө
  AlpinDale ea0f57b233 feat: allow further support for non-cuda devices (#247) 1 жил өмнө
  AlpinDale 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 жил өмнө
  AlpinDale c0aac15421 feat: S-LoRA support (#222) 1 жил өмнө
  AlpinDale 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) 1 жил өмнө
  AlpinDale f013d714c0 chore: merge dev branch into main (#177) 1 жил өмнө
  AlpinDale 2755a48d51 merge dev branch into main (#153) 1 жил өмнө
  g4rg 28fa4ae213 fix: cpu memory limit detection for containers (#103) 1 жил өмнө
  AlpinDale efc6f7fbec chore: reformats (#90) 1 жил өмнө