ATC/atc-GPU
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add GPU Lab configs, docs, and runbooks for VM303.

Browse Source 
Mirror gpu-lab compose files and model-manager catalog from GPU-Dev; document Dockhand mapping and SGLang cutover target.
This commit is contained in:
mo
2026-06-04 02:24:57 +02:00
parent 26aec9ed04
commit c154c94c6d
14 changed files with 930 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/landscape.md
+30
View File
@@ -0,0 +1,30 @@
# GPU Lab Landscape
## Nodes
| Host | IP | Role |
|------|-----|------|
| VM303 GPU-Dev | 10.0.20.106 | GPU Lab UI (:9000), inference (:8010), gateway (:8001) |
| atc-docker01 | 10.0.21.45 | Homepage, Dockhand (:8082) |
| Bart-GPU | — | Reference node (documented in model-manager) |
| Mo-GPU | — | Reference node |
## VM303 specs
See `config/model-manager/vm-specs.json`: 4× Tesla V100 32GB, Docker with NVIDIA runtime.
## Inference runtimes
Only one runtime is active at a time on port **8010**:
| Runtime ID | Engine | Compose file |
|------------|--------|--------------|
| `vllm-legacy-040` | vLLM 0.4.x | `compose.vllm-legacy.yml` |
| `vllm-modern-080` | vLLM 0.8.x | `compose.vllm-modern.yml` |
| `sglang-modern` | SGLang 0.5.12 | `compose.sglang.yml` |
Models live under `/root/models/` on VM303 (not in git).
## Docker data
Images stored under `/root/docker-data` (avoid small `/var` partition).