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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Installation]: ROCm install silently falls back to CUDA abi3 wheel on Python < 3.12 (no ROCm abi3 / cp311 / cp313 wheels)
- [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+)
- add cute helion kernel
- [Test][Quantization] Restrict test_machete_mm gate to Hopper family
- [Spec][PP] Support MTP speculative decoding under pipeline parallelism (PP>1)
- [CI] Add opt-in statistically-calibrated lm-eval accuracy gate (Wilson lower bound)
- fix(kv_cache): domain-tag LoRA and cache_salt prefix-cache keys to prevent collision (#44701)
- [ROCm CI] 90% parity on AMD's test group gating status/mirroring by AMD Advancing AI July 22 2026
- [ROCm Test-First CI]: Day 0 vLLM MI455X UALoE72 Helios Rack open source community upstream CI by AMD Advancing AI July 22 2026
- [Rust Frontend] Add Granite tool and reasoning parsers
- Docs
- Python not yet supported