vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Support sequence parallelism for Qwen3Next
- [WIP][CT][XPU] Add `W8A16_FP8` Linear Support
- [Bug]: Multiple tool_calls parsed correctly by hermes_tool_parser, but fail in serving_chat.py with JSONDecodeError
- [Feature]: batch invariance for A100
- [RFC]: Tracking follow-up progress on Encode–Prefill–Decode Disaggregation
- [Refactor] Make Int8ScaledMMLinearLayerConfig to use QuantKey
- [BugFix] Support DP/EP in AG/RS for FLASHINFER_CUTLASS FP8
- [Bug]: CPU tests hit CUDA path when VLLM_TARGET_DEVICE=cpu [CPU Backend]
- [RFC]: [P/D] Prefill compute optimizations with bi-directional KV cache transfers between P and D nodes
- Factor out masked-m format silu_mul_quant and use it in BatchedTritonExperts
- Docs
- Python not yet supported