Skip to content

Instantly share code, notes, and snippets.

View chawasit's full-sized avatar

Chawasit Tengtrairatana chawasit

View GitHub Profile
@sammcj
sammcj / glm-4_7-flash-vllm.md
Created January 27, 2026 21:06
GLM 4.7 Flash vLLM, 2+ RTX 3090, 105-120tk/s
services:
  &name vllm:
    <<: [*ai-common, *gpu]
    container_name: *name
    hostname: *name
    profiles:
      - *name
    # image: vllm/vllm-openai:cu130-nightly
    build: