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 supported24 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- fix: Add SWIGLUSTEP activation support for ROCm AITER MoE
- [Attention] Improve attention benchmarks: configs and profiling
- fix: Fallback to torch for context_len > 2048 to bypass aiter kernel bug
- feat[vLLM × v5]: Add audio support for the Transformers backend
- [Refactor][MLA]: Expose mla to torch.compile
- [Core][Scheduler] Simulate reclaimable KV cache blocks before preempting running requests
- [Perf] Skip decode for generative scoring with max_tokens=0
- [Attention] Add HPC attention backend for improved performance on SM90 GPUS
- [Bug]: Gemma 4 31B FP8_BLOCK checkpoint produces garbage repetitive output — logit saturation at softcap wall due to absorbed activation scales being double-applied
- [Bugfix] Support Qwen3.5 Text Only Variant (Qwen3_5ForCausalLM)
- Docs
- Python not yet supported