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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Avoid HTTP 200/null responses on client disconnect
- [ROCm] Fix ROCm Attention Backend Slection
- [Bugfix][Model Loader] Make `model.load_weights` safe to invoke on already-initialized model
- [KVConnector][P/D][Tests] Add tests for KV transfer completion during shutdown
- [Model][Hardware][AMD][Kernel]: Part 2/2 -> Enable e2e QK Norm + RoPE + KV Cache runtime fusion for Qwen3-30B-A3B on ROCM_ATTN
- [Quantization] Add ModelOpt FP8/NVFP4 weight-only embedding methods
- [Feature][KVConnector] Add optional get_eviction_order hook for policy-driven free-queue ordering
- [Bugfix] WeightsMapper: make orig_to_new_suffix idempotent
- [Observability] Add structured per-request context to preemption warnings
- [feature] shuffle safetensor weight files
- Docs
- Python not yet supported