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
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [RFC]: ReplaySSM: cache SSM inputs instead of state for faster standard and speculative decode (Mamba2 + GDN)
- [DSv4 Perf] Optimize workspace reuse for eager break, 3.9% E2E TTFT improvement.
- POST /wake_up fails with AttributeError: 'list' object has no attribute 'zero_' in init_fp8_kv_scales, wedging the engine (health stays green, completions hang)
- [Bug]: Decode instance segfaults on NIXL `loadRemoteMD` after prefill pod restarts in P/D disaggregation
- Malformed /v1/responses request returns a >100MB validation-error body (full input echoed per error)
- [Bugfix] Dispatch python builtin tool call in ParsableContext
- [Core][PCP] Support data parallelism with MRV2 PCP
- [Bug]: glm47 tool parser silently returns empty arguments when the model omits the opening <arg_value> tag
- [Bugfix] glm47 parser: tolerate missing opening <arg_value> tag
- [Bug]: kv_load_failure_policy="recompute" gives wrong output when a KV connector rejects a synchronous load (V2 runner)
- Docs
- Python not yet supported