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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- add last_engine_iteration_timestamp_seconds in metric.
- Fix: Prevent RuntimeError in DeepGEMM warmup by deferring alignment check for non-FP8 modules
- Bump llguidance to 1.7
- [Perf] Flashinfer fp8 quant
- [Bugfix][V1] Defensive guard for stale req_id in `_update_after_schedule`
- [Performance]: Qwen3-VL-235B-A22B-Instruct NVFP4 Performance dropped at upstream main
- [Spec Decode] Allow DFlash drafter to coexist with quantized target KV via independent KV groups + dtype override
- [XPU] Add GPTQ INT4 quantization support for XPU platform
- fix(eagle3): read norm_before_fc from eagle_config for NVIDIA checkpoint
- Add MolmoWeb architecture wrapper
- Docs
- Python not yet supported