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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: TP=2 DP=2 Broken for Qwen3-Next W4A16
- [Test] Add basic unittests for `split_graph`
- [AMD] fix to run MLA with kv cache dtype = fp8
- [Bug]: Validation Error: block_size (2096) > max_num_batched_tokens (2048) when enabling prefix caching for Qwen3.5 Mamba architecture
- [Core] Remove FlashAttention block size restriction for hybrid models
- [Doc] Fix typos in comments: i.e./e.g. punctuation and "archive" -> "achieve"
- [Doc] Fix grammatically incorrect error message in gpu_worker and xpu_worker
- [Usage]: When running qwen3.5-27b with vllm 0.17.0, the Deep Thinking output is under "reasoning" and not under "reasoning_content".
- [Bugfix] Fix Eagle3 aux_hidden_state_layers indexing with pipeline parallelism
- [Bug]: Qwen3.5-35B-A3B-FP8 inference output terminates unexpectedly, logs show normal but request hangs
- Docs
- Python not yet supported