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 supported35 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [CI/Build] Regression test: CPU MoE activation table must not require a config context
- [Bug/Perf]: hybrid-SWA prefix caching collapses to zero for ALL requests in multi-session round-robin at ~25% pool occupancy (Gemma-4-31B; eager-freed SWA tails recycled tail-first)
- [KV Offload] Bypass power-of-2 rounding in KV offload CPU pinned allocation
- [RFC]: Support SparDA-style decoupled Forecast projection for lookahead KV prefetch in sparse attention
- [Bug]: MiniCPM-V-4.6 fails to load on vLLM 0.25.0 — ValueError: There is no module or parameter named 'qkqkv_proj' in MiniCPMV4_6ViTWindowAttentionSelfAttn
- [Bugfix] Bound Responses API in-memory store
- Re-enable DBO accuracy test on Blackwell
- [Bugfix] Exclude DSpark draft-model KV-cache group from core prefix-cache lookup veto
- Apply current settings to Harmony continuations
- [V1] Add generic imperative KV-connector step lifecycle helpers
- Docs
- Python not yet supported