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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Helion] Route fusion-only kernels to Helion during CUDA-graph capture
- [Feature]: nvfp4 KV cache on SM120 — flashinfer ships the kernels, vLLM isn't wired to them (working prototype, 245K ctx on a 5090)
- [Bug]: nvfp4 reshape_and_cache_flash assumes NHD layout — silently mis-swizzles HND caches when num_kv_heads % 4 == 0
- [Doc] Add stream tracker middleware example for live per-request visibility
- fix(v1): avoid false shutdown failures on clean exit
- fix: handle missing parent modules in _has_module
- [Perf] Add per-phase cold-start startup span benchmark harness
- Make `load_weights` completely optional
- [Perf][MRV2] use FlashInfer AIR for for top-p rejection sampling
- [Bug]: Ministral is broken with --kv-cache-dtype fp8 in 0.25.1
- Docs
- Python not yet supported