daaf85f4e5
Switch to bridge networking with fixed container port 80 and served name llm
...
- run.sh: bridge + -p ${HOST_PORT:-24396}:80, health check uses host port
- entrypoint.sh: PORT defaults to 80, SERVED_NAME defaults to llm
detected port/served name become log hints only
- verify.sh: read host port from port bindings, expect model name llm
- docker-compose.yml: ports mapping instead of network_mode host
- README: update tables, commands and rationale
2026-10-28 14:19:42 +08:00
31994d940f
Document the published CI image and its docker run commands
2026-10-28 13:34:58 +08:00
d0e260c322
Keep image generic; move startup settings into run.sh/compose
Docker Build and Push / docker (push) Successful in 1h29m12s
2026-10-26 18:53:54 +08:00
9f523e208a
Use unique ModelHub framework name vllm_llama_4
Docker Build and Push / docker (push) Has been cancelled
2026-10-26 18:33:01 +08:00
53063f60ee
Document verify usage without docker
Docker Build and Push / docker (push) Has been cancelled
2026-10-26 17:01:53 +08:00
4857faec4e
Improve verify auto-detection without docker
2026-10-26 17:01:28 +08:00
9000c3ab0e
Allow TP/PP/PORT/SERVED_NAME overrides in compose
2026-10-26 17:00:38 +08:00
738d9f80e4
Auto-detect Scout/Maverick from config.json and add verify script
2026-10-26 16:59:44 +08:00
13f14a12e9
Add provenance note
2026-10-26 16:28:06 +08:00
55166056ef
Note Maverick task type option
2026-10-26 16:25:52 +08:00
c3255420bb
Document compose overrides and CI runner requirements
2026-10-26 16:25:15 +08:00
caddeadd15
Unified Llama 4 Scout/Maverick BI-V150 deployment bundle
2026-10-26 16:24:16 +08:00
