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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Add H20-3e FP8 fused-MoE tuned config for E=256,N=512 (Qwen3.6 A3B)
- [Kernel] Support more topk values in moe_sum kernel
- Refactor MoE Oracles to use base class MoEKernelOracle
- [Bugfix][Spec Decode] Derive num_speculative_tokens from a speculators draft config
- Remove unnecessary `load_weights` methods
- Add Thor selective state update configs
- Fix empty DP model step coordination
- [Bug]:correct prompt_tokens_details.cached_tokens under PD disaggregated mode
- [FRONTEND]: forward VLLM_ENGINE_READY_TIMEOUT_S to Rust frontend via --args-json
- [Structured Output] Limit whitespace in JSON schema FSM to prevent runaway whitespace (issue #38696)
- Docs
- Python not yet supported