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
- [Bug]: verify_with_parallel_config rejects DCP-over-PCP topologies that ParallelConfig accepts
- [ROCm][Perf] Kimi-K3 latent-MoE: overlap the shared all-reduce with the routed up-projection
- [Model Runner V2][Spec Decode] Only embed MM inputs during multi-layer MTP
- [Bugfix][Rust Frontend] Return an error instead of panicking on empty-prompt logprobs
- [RFC]: DP pause/sleep correctness: coordinator latch, request admission, device-idle completion, and sleep/pause layering
- [Bug] DeepSeek-V4 sparse prefill crashes (FlashMLA/SM90, phase1.cuh:614) on 0-token KVTransfer prefill requests
- [Core] Reject new requests while generation is paused
- [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
- Docs
- Python not yet supported