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 supported30 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Segfault encountered in qwen3.5-27B long video (>2G)inference
- [Don't Merge][WIP][XPU][TEST]add intel full ci job yamls
- Feat/invariant with prefix cache
- [Bugfix][DSv3.2] Skip indexer weights for index-cache-skipped layers
- [Usage]: when MTP is enabled, what tokens will be sent to draft model every time?
- [Frontend] Add Streaming Parser Engine and new Kimi k2.5/k2.6/k2.7 Parser
- [Bug]: No available shared memory broadcast block found in 60 seconds. This typically happens when some processes are hanging or doing some time-consuming work (e.g. compilation, weight/kv cache quantization).
- [Bugfix] Raise VLLMValidationError for non-integer logit_bias keys
- [RFC]: KVarN: a calibration-free, variance-normalized sub-8-bit KV-cache quantization backend
- [Doc]: vLLM 0.23.0 + Qwen3-VL-8B-Instruct-FP8 on RTX 5080 (Blackwell) - Engine initializes but generate() hangs silently
- Docs
- Python not yet supported