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 supported52 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: FlashInfer-CUTLASS NVFP4 MoE lacks SWIGLUSTEP activation (blocks Step-3.7-Flash-NVFP4 at TP=8)
- [Spec Decode] Fix speculators-format DSpark loading; mirror repetition penalty on DSpark draft logits
- [Benchmark] KV Cache Offload Benchmark — Block Copy Performance
- Fix special-token leakage into content when tools/tool_choice is omitted on a later agent-loop turn
- [Docs] Add Llama-3.1-8B-Instruct to batch invariance tested models
- [Bug][XPU]: gpt-oss-120b (MXFP4 MoE, TP=2) corrupt under piecewise XPU graph capture on Data Center GPU Max 1100 (PVC); compile-mode correct
- [Rust Frontend] Fix bad_words handling in /v1/completions
- [ROCm][MoE] Avoid redundant AITER MXFP8 MoE output copy
- [DO NOT REVIEW][Kernel][Helion] Retune SiLU FP8 schedules on H100
- [Kernel][Helion] Retune dynamic quant schedules on H100
- Docs
- Python not yet supported