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
- [Bug]: Scheduler livelock with multi-module MTP + Mamba align prefix caching when prompt_len % block_size < num_speculative_tokens
- [Observability] Add tool-calling telemetry to HTTP render endpoints
- [Bugfix] Retry multimodal cache misses in common endpoints
- [RFC]: Bring-Your-Own-GPU (BYOG) reproducible evals and benchmarks for PRs
- [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
- Docs
- Python not yet supported