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 supported42 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: thinking_token_budget forces reasoning_end tokens into the middle of tool-call arguments — ThinkingBudgetStateHolder doesn't treat <tool_call> as implicit reasoning end (Qwen3.5+)
- [Spec][PP] Support MTP speculative decoding under pipeline parallelism (PP>1)
- fix(kv_cache): domain-tag LoRA and cache_salt prefix-cache keys to prevent collision (#44701)
- [Rust Frontend] Add Granite tool and reasoning parsers
- fix(scaled_mm): use reshape to accept non-contiguous activations
- [Bugfix] Fix shape mismatch crash and add logprob_token_ids support in RejectionSampler
- [Responses] Support required function tools for GPT-OSS Harmony
- [Doc] Add INT8 batch-size throughput caveat to BitsAndBytes docs
- [Performance]: Qwen3.6-35B-A3B-FP8 on RTX PRO 6000 Blackwell has very low decode throughput; missing FP8 MoE config for E=256,N=256
- [Bugfix] Normalize non-standard message roles from Claude Code CLI >= 2.1.154
- Docs
- Python not yet supported