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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug][KV Offload]: Direct-layout offload is treated as parallelism-agnostic, so engines with different TP sizes sharing a secondary tier load corrupted KV
- [Perf][Attention] Fuse DCP correction output layout for reduce-scatter
- [Bugfix][Benchmark] Fix standalone dataset statistics plotting
- [Bugfix][Multimodal] Normalize native-rate PyAV audio
- [Backport][0.32] Preserve Clef Flash context and cold-cache behavior
- [Bugfix][Parser] Honor a prompt-closed reasoning block for PLaMo3
- [CI] Avoid nested CUPTI control in bench forward profiles
- [Bug]: Hybrid GDN models (Qwen3.5) with n-gram speculative decoding: greedy outputs go wrong when drafts are partly accepted; the GDN state misses the last accepted token's update
- [Bug]: kv_transfer_params.prompt_token_ids replaces the rendered chat prompt on servers with no KV connector
- [XPU] support adaptive verification for deepseek-v4
- Docs
- Python not yet supported