GitDeployHub

0xsero/kimi-k2-6-nvfp4-sglang

github.com/0xsero/kimi-k2-6-nvfp4-sglang ↗

By using gitdeployhub.com, you agree to our Terms and Privacy. Each deploy host has its own terms; clicking a deploy button takes you to that host’s flow.

Docker
20 environment variables found in .env.example

Set these on your host before deploying. Each platform has an “Environment Variables” section in the deploy flow. (showing first 20, more exist in .env.example)

  • MODEL_DIR Host paths.
  • LOG_DIR
  • METRICS_DIR
  • HF_MODEL_ID Hugging Face source.
  • CONTAINER_NAME Container identity.
  • SGLANG_BASE_IMAGE
  • SGLANG_IMAGE
  • CUDA_VISIBLE_DEVICES GPU placement. The verified host used four RTX PRO 6000 Blackwell GPUs.
  • CUDA_DEVICE_ORDER
  • HOST Public API.
  • PORT
  • SERVED_MODEL_NAME
  • TP_SIZE SGLang model settings.
  • PP_SIZE
  • CONTEXT_LENGTH
  • MAX_RUNNING_REQUESTS
  • MEM_FRACTION_STATIC
  • CHUNKED_PREFILL_SIZE
  • MAX_PREFILL_TOKENS secret
  • PAGE_SIZE
Best match Fly.io Anything Dockerized — requires the Fly CLI.
macOS 
brew install flyctl && fly launch --from https://github.com/0xsero/kimi-k2-6-nvfp4-sglang
Linux 
curl -L https://fly.io/install.sh | sh && fly launch --from https://github.com/0xsero/kimi-k2-6-nvfp4-sglang
Windows (PowerShell) 
iwr https://fly.io/install.ps1 -useb | iex; fly launch --from https://github.com/0xsero/kimi-k2-6-nvfp4-sglang
Alternative Deploy on Railway Apps that need Postgres, Redis, or background workers.
Or deploy to a different host
Render Full-stack with managed Postgres + Redis. DigitalOcean App Platform Containers, droplets, and managed services.
← Try another repo