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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][ROCm] Fix DSA MoE skip_final_all_reduce assert with MoRI/DeepEP at TP=1
- [Feat][Stacked] Add bidirectional single-forward reads for Nemotron fine-tunes
- Fix non-deterministic greedy decoding across repeated generate() calls
- [ROCm][BugFix][FP8] Pad weights and inputs to fix TP8 crash in ROCmFP8ScaledMMLinearKernel
- fix(rust/chat): accept latest_reminder role in DeepSeek V4/V4.1 renderer
- [Bugfix] Keep the --tokenizer chat template for multimodal models
- [Perf][Structured Output] Parallel guidance bitmask fill: 15% faster decode at batch 64
- [MoE] Support REAP-pruned and MoNE checkpoints with non-uniform per-layer expert counts
- [Perf][Kernel] Tune fused mHC post + pre-norm for SM90 at up to 8 tokens
- [Bugfix][Mamba] Warm up V1 align state copies and ShortConv prefill
- Docs
- Python not yet supported