llm-d incubation
Incubating components of llm-d, a Kubernetes-native high-performance distributed LLM inference framework
Popular repositories Loading
-
-
llm-d-modelservice
llm-d-modelservice Publichelm charts for deploying models with llm-d
-
llm-d-fast-model-actuation
llm-d-fast-model-actuation PublicKubernetes controllers for fast model actuation using vLLM sleep/wake and launcher-based model swapping
-
batch-gateway
batch-gateway PublicThe batch gateway is an llm-d implementation of the OpenAI batch inference API
Repositories
Showing 9 of 9 repositories
- ig-wva Public
Workload Variant Autoscaler is a service to compute the cost-optimal provisioning of heterogeneous accelerators for inference workloads with varying request latency objectives
llm-d-incubation/ig-wva’s past year of commit activity - llm-d-fast-model-actuation Public
Kubernetes controllers for fast model actuation using vLLM sleep/wake and launcher-based model swapping
llm-d-incubation/llm-d-fast-model-actuation’s past year of commit activity - llm-d-ci Public
llm-d-incubation/llm-d-ci’s past year of commit activity - llm-d-async Public
llm-d-incubation/llm-d-async’s past year of commit activity - secure-inference Public
llm-d-incubation/secure-inference’s past year of commit activity - hermes Public
Hermes is a cluster configuration scanning and self-test generation tool for llm-d inference workloads
llm-d-incubation/hermes’s past year of commit activity
Top languages
Loading…
Most used topics
Loading…