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 supported52 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Demote FlashInfer CUTLASS unquantized MoE when intermediate size is not 128-aligned
- [New Model]: nvidia/LocateAnything-3B (slow autoregressive mode first)
- [Benchmark] Use sliding windows for peak serving metrics
- [Security] Fix P2P ZMQ socket exhaustion via unbounded peer sessions
- fix: prevent NIXL Decode worker crash from multi-prompt completions
- [Bugfix][Kernel] Hoist tensor-descriptor build out of unified-attention TD tiβ¦
- [UX] Emit warning if some decode batches are not covered by CUDA graphs
- [RFC]: Unify functional P2P gating β one veto-only verdict for all P2P consumers (NCCL, custom allreduce, symm-mem)
- MooncakeConnector P/D: NVLink fallback transfer fails "Requested address not found" (fp8 MLA, v0.25.0)
- DeepSeek-V4 (deepseek_v4): fused topk_softplus_sqrt router rejects non-standard expert counts on CUDA (REAP 144-expert ckpts); torch fallback is XPU-gated
- Docs
- Python not yet supported