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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [RFC]: Adaptive throughput/latency profile for RL rollout long-tail
- [Feature]: Support Dynamic Pruning for Speculative Decoding Draft Trees in EAGLE-3
- [Feature]: --kv-transfer-config unconditionally disables HMA, ignoring SupportsHMA on the connector
- [Performance]: KV prefetching not spawned on time can cause unnecessary GPU idle
- [Bugfix] Use NVFP4 packed layout for SlidingWindowSpec.real_page_size_bytes
- [MM][Perf][CG] Support ViT full CUDA graph for InternVL
- Fix #30128
- Fix: merge default stop_token_ids with request stop_token_ids in to_sampling_params
- [Bug]: FLASH_ATTN_DIFFKV crashes on init with
- [ROCm][Perf] Fix RMSNorm+Quant fusion for gfx950 (non-fnuz)
- Docs
- Python not yet supported