< cd ../gallery
[AI & ML]
GLM-spark by bird
Serve GLM-5.2 469B (REAP-pruned, NVFP4) across 3× NVIDIA DGX Spark with vLLM pipeline parallelism — 256K context, production-ready config and patches. Maintained by bird on GitHub, where it has earned 27 stars from the community.
# install
pip install glm-sparkmore vLLM repos
AI & ML
A REST API for vLLM, production ready. Maintained by France-Travail on GitHub, where it has earned 29 stars from the community.
12mo ago
AI & ML
A hybrid router that uses Spot GPU instances to reduce costs and Serverless GPUs for making Cold Starts faster. Maintained by Tandemn-Labs on GitHub, where it has earned 27 stars from the community.
7mo ago
AI & ML
A simple service that integrates vLLM with Ray Serve for fast and scalable LLM serving. Maintained by asprenger on GitHub, where it has earned 79 stars from the community.
2y ago
