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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Build] Fix Dockerfile issues for ppc64le build
- [Model] Add AnyModel: generic support for NAS-optimized heterogeneous architectures
- [Bug Fix] Defer record_metadata_for_reloading to avoid ~3x host memory regression
- [Bugfix] Fix TypeError during AWQ Marlin MoE loading by unwrapping traced tuple
- Add GlmOcrConfig with fixes, E2E test, and generic config registry validation
- [CI] Add Blackwell DeepSeek MTP acceptance length regression test
- [Bug]:Qwen3.5-35B-A3B vllm v0.17.0 ERROR 03-10 00:52:24 [multiproc_executor.py:261] Worker proc VllmWorker-0 died unexpectedly, shutting down executor.
- [Hardware][NVIDIA] Set NCCL_P2P_DISABLE=1 on non-fully-connected CUDA topology
- [Kernel] Flush L2 cache in benchmark_moe to reduce cache warmth bias
- [Performance]: qwen3.5 vs qwen3
- Docs
- Python not yet supported