A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
main
[CI] Raise VLLM_MAX_SIZE_MB to 500 due to failing Build wheel - CUDA 12.9 (#26722)
Michael Goin committed about 1 year ago
Update coveragerc and add codecov.yml for path fixes (#26435)
Reza Barazesh committed about 1 year ago
[Config] Remove Unused Environment Variable `VLLM_DISABLE_PAD_FOR_CUDAGRAPH` (#26743)
Wentao Ye committed about 1 year ago
Revert "[issues template] Encourage the author implement their own ideas" (#26814)
wang.yuqi committed about 1 year ago
[Feature][Responses API] Stream Function Call - harmony (#24317)
Chauncey committed about 1 year ago
[KVConnector][Metrics] Aggregate scheduler-side KVConnectorStats (#26046)
Qier Li committed about 1 year ago
[issues template] Encourage the author implement their own ideas (#26671)
wang.yuqi committed about 1 year ago
use combo kernel to fuse qk-norm and qk-rope (#26682)
Boyuan Feng committed about 1 year ago
Adjusted the model order of the model registration file (#26798)
汪志鹏 committed about 1 year ago
[DCP] Support Decode Context Parallel (DCP) for GQA with FlashAttention (#24864)
Jaya Yuan committed about 1 year ago
[CI/Build] Cleanup LoRA test (#26752)
Jee Jee Li committed about 1 year ago
[Feature] Change vllm.py with pydantic validation (#26726)
Vladislav Bronzov committed about 1 year ago
[Chore] Remove `SupportsV0Only` interface and update supported models docs (#26783)
Cyrus Leung committed about 1 year ago
[CI] Fix test_tool_id_kimi_k2 (#26787)
Chauncey committed about 1 year ago
[Doc] ruff format some Python examples (#26767)
Cyrus Leung committed about 1 year ago
Don't allow `typos` to fix by default (#26785)
Harry Mellor committed about 1 year ago
[Chore] Use `max_transformers_version` for Qwen-VL test (#26792)
Cyrus Leung committed about 1 year ago
[NIXL][HeteroTP] Enable KV transfer from HND prefill to NHD decode (#26556)
Chendi.Xue committed about 1 year ago
[Model] Use merge_by_field_config for MM models (O-P) (#26776)
Cyrus Leung committed about 1 year ago
[Bugfix] Standardize merging multimodal embeddings (#26771)
Cyrus Leung committed about 1 year ago