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
- [KVCache] Support Pluggable KVCacheSpec
- refactor hard coded device string in test files under tests/v1 and tests/lora
- [Bugfix] Handle ParallelLMHead in compressed-tensors get_quant_method
- [Bugfix][Model] Fix Kimi K2 tool parser 8KB section limit and simplify streaming state
- [Perf] Optimize hidden state extraction logic
- [ROCm][Quantization] fallback trust_remote_code=True in Quark config for some cases
- [Bugfix] Fix KV cache sizing and allocation for hybrid Mamba/attention models
- [Bugfix] Fix for builtins (forward fix of pytorch/177558)
- Fix ambiguous num_blocks for hybrid attn mamba
- [MoE] Introduce Fp8PrepMixin and class-based dispatch for DeepGemm
- Docs
- Python not yet supported