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
Add a CodeTriage badge to vllm
Help out
- Issues
- [Docs] Document DeepSeek-V4 reasoning_effort normalization
- vLLM lacks Blackwell unified-memory paging telemetry — reference mapping exists in dgx-spark-monitoring
- [Bugfix][Spec Decode] Avoid temporary Qwen3.5 MTP vocab allocations
- [MoE] Re-enable TRITON_UNFUSED in the gpt-oss MXFP4 dispatch list
- [Feature]: Add explicit cache IDs for reusable multimodal and inference state
- [Bugfix] Initialize video pruning for Qwen3.5
- [Bugfix] Exclude the compilation peak from memory profiling
- [ROCm] Enable Navi custom paged attention at gqa_ratio 1 and 2
- [Bugfix][Executor] Avoid false worker shutdown on spurious sentinel readiness
- [Model] Migrate Gemma4DSpark to AutoWeightsLoader
- Docs
- Python not yet supported