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 supported25 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug/Feature] TurboQuant + Hybrid MoE (Qwen3.6-35B-A3B) broken on Ampere (SM 80-86) — 13 patches with fixes
- [Bug]: `ROCM_AITER_MLA_SPARSE` prefill produces garbage for prompt_len > ~20K tokens on gfx950 (GLM-5.1-FP8)
- fix(vllm): port skip_kv_gather check and workspace reservation to ROCm MLA sparse attention
- [Feature]: Per-request timing metrics in response body
- perf: use set lookup for special tokens in _reduced_vocabulary
- perf: replace encode() with get_vocab() in isaac.py
- docs: fix doc-code mismatches from audit
- [WIP] Prototype pre-spawn EngineCore to overlap child imports with parent init
- Fix Step-3.5 MTP layer type lookup
- Delay unstable GLM tool names in streaming
- Docs
- Python not yet supported