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
- [Perf][MoE] Wrap GateLinear ll_bf16_gemm in custom op to prevent torch.compile branch freezing
- [Feature] Red-Green watermarking
- [Bug] pause_generation(mode="keep", clear_cache=True) raises when a streaming-input session is parked between turns
- [Bug]: grouped_topk selects wrong experts with more than eight groups
- [Bug]: Qwen3.5 (hybrid GDN) models cannot run dflash speculative decoding with pipeline parallelism (missing supports_aux_hidden_states_over_pp opt-in)
- [Bugfix] Use native memory fence for SHM broadcasts
- [Frontend] Support image inputs in the Decisions API
- docs(envs): fix stale VLLM_CPU_KVCACHE_SPACE default comment (follow-up to #60048)
- [Bug]: `--mamba-block-size` has no effect in any valid configuration after the removal of `mamba_cache_mode="all"`
- [Bug]: glm47 streaming parser silently swallows the rest of the stream (including the real tool call) after a stray `<tool_call>` token in prose
- Docs
- Python not yet supported