Public KG record
llm-d
Recorded overview
KG-recorded product related to llm-d; detailed English notes are not yet available.
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Benchmarks: 17,000-node GKE benchmark
- Deployment: Google Cloud GKE Inference Gateway 可托管路由器
- Integrations: 基于 Kubernetes Gateway API Inference Extension
- License: Apache 2.0
- Maturity: 1.0 首个稳定版本，面向生产运行
- Maturity: 1.0 是首个稳定版本
- Performance: 中位数 TTFT 下降超过 85%
- Performance: 吞吐量达到 2.4 倍
Evidence coverage
The KG currently records 9 known information dimensions and has 9 undocumented dimensions, linked to 1 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Google Cloud — releases
- NVIDIA Dynamo — related to
- AIBrix — related to
- 17,000-node GKE benchmark — evaluated on
- CNCF — part of