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 supported36 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Fix int4_per_token_head for SWA models and gemma 4
- [Bug]: Gemma4 MTP speculative decoding crashes at engine init on 0.25.1 — "a and b must have same reduction dim" (regression from 0.21.0)
- [Bug]: disable_any_whitespace is silently ignored at the request level (xgrammar)
- [Bug]: The Deepseek v4 model compiles kenrel during the inference process
- [Bug]: sample_tokens RPC timeout with GLM-5.2-FP8 + DSpark speculative decoding, TP=8 across 2 nodes (Blackwell GB200)
- [Model] Add Inkling multi-depth MTP support [5/N]
- [Profiler] Add Triton Proton profiling backend
- [RFC]: Context-length-aware speculative token scheduling — extending num_speculative_tokens_per_batch_size with a context-length axis
- [ROCm][CI] Reuse equivalent ROCm CI images
- transformers backend: tensor reshape error during profile run with GLM MoE architecture
- Docs
- Python not yet supported