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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Usage]: vLLM 0.24.0 crashes on startup with Qwen3.6-27B-FP8 on Blackwell SM120 — DeepGemm warmup ignores auto-disable
- [CI] Add GSM8K accuracy configs for Blackwell NVFP4/FP8 models
- [CI] Add GSM8K accuracy configs for large NVFP4/INT4 MoEs (4xB200)
- Model Runner V2 Remaining TODOs
- [Usage]: DeepSeek-V4: --kv-cache-dtype auto fails silently on Blackwell SM120 — should auto-resolve to fp8_ds_mla
- [Bugfix][Frontend] GLM-4.7: guided-decode forced tool calls when strict tool-calling is disabled
- [Rust Frontend] Validate structured-output requests to match Python
- Torch Stable ABI pre-commit hook
- [Bugfix] Fail fast with a clear error when CPU offload region exceeds available space
- [Performance]: Impact of Full Cuda Graph on different model sizes, batch size on B200
- Docs
- Python not yet supported