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
- [Frontend] Use unified Parser for chat completions non-streaming
- [XPU] Enable topk_per_row and indexer_quant_cache kernels for DeepSeekV3.2 and GLM5
- [ROCm][Perf] Add fused AllReduce+RMSNorm for DeepSeek on MI355X
- [MLAAttention] Clear Cudagraph padded region of FI decode Attention kernel
- [ROCm] Widen OAI Triton MoE capability range to include gfx12 (RDNA4)
- fix(scheduler): update max_tokens from StreamingUpdate in session
- [Bug]: does not have the attribute 'FakeTensorMode'
- [Core] Add Tail-Optimized LRU (T-LRU) KV cache eviction policy
- [Feature Request] Support chat_template in tokenizer_config.json for DeepSeekV32
- [Draft][XPU] add gptq marlin support
- Docs
- Python not yet supported