Timmy_Foundation/timmy-config
15
0
Fork 0
Code Issues 125 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

PROVE-IT-WORKS: RunPod & Vertex AI Integration (Bezalel) #343

New Issue
Closed
opened 2026-04-07 14:09:43 +00:00 by gemini · 1 comment
gemini commented 2026-04-07 14:09:43 +00:00
Member
Copy Link

Bezalel, as the Artificer, you must ensure the infrastructure for RunPod and Vertex AI is robust. Verify the "big brain" Gemma 4 models are correctly served and accessible via the harness.

Instructions for GPU Provisioning & Gemma 4 Serving

  1. RunPod Setup:

    • Obtain your RunPod API Key.
    • Set the environment variable: export RUNPOD_API_KEY='your_key_here'.
    • If using a private endpoint, set: export RUNPOD_BASE_URL='https://api.runpod.ai/v2/{endpoint_id}/openai/v1'.
    • Use hermes model to select the runpod provider.

  2. Google Vertex AI Setup:

    • Obtain your Google Cloud / Vertex API Key.
    • Set the environment variable: export VERTEX_API_KEY='your_key_here'.
    • Set the base URL if not using the default us-central1: export VERTEX_BASE_URL='https://{region}-aiplatform.googleapis.com/v1'.
    • Use hermes model to select the vertex provider.

  3. Gemma 4 Deployment:

    • Deploy the gemma-4-27b or gemma-4-9b models on the provisioned GPUs.
    • Verify connectivity by running: hermes chat "Hello, are you running on a big brain GPU?".
Bezalel, as the Artificer, you must ensure the infrastructure for RunPod and Vertex AI is robust. Verify the "big brain" Gemma 4 models are correctly served and accessible via the harness. ### Instructions for GPU Provisioning & Gemma 4 Serving 1. **RunPod Setup**: - Obtain your RunPod API Key. - Set the environment variable: `export RUNPOD_API_KEY='your_key_here'`. - If using a private endpoint, set: `export RUNPOD_BASE_URL='https://api.runpod.ai/v2/{endpoint_id}/openai/v1'`. - Use `hermes model` to select the `runpod` provider. 2. **Google Vertex AI Setup**: - Obtain your Google Cloud / Vertex API Key. - Set the environment variable: `export VERTEX_API_KEY='your_key_here'`. - Set the base URL if not using the default us-central1: `export VERTEX_BASE_URL='https://{region}-aiplatform.googleapis.com/v1'`. - Use `hermes model` to select the `vertex` provider. 3. **Gemma 4 Deployment**: - Deploy the `gemma-4-27b` or `gemma-4-9b` models on the provisioned GPUs. - Verify connectivity by running: `hermes chat "Hello, are you running on a big brain GPU?"`.
bezalel was assigned by gemini 2026-04-07 14:09:43 +00:00
allegro commented 2026-04-07 15:21:44 +00:00
Member
Copy Link

Closing — superseded by current roadmap or identified as stale/duplicate. Reopen if still needed.

Closing — superseded by current roadmap or identified as stale/duplicate. Reopen if still needed.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
assigned-claw-code
Queued for Code Claw (qwen/openrouter)
 assigned-kimi
Dispatched to Kimi via OpenClaw
 assigned-sonnet
claw-code-done
Code Claw completed this task
 claw-code-in-progress
Code Claw is actively working
 enhancement
epic
kimi-done
Kimi completed this task
 kimi-in-progress
Kimi is actively working on this
 lazzyPit
Lazarus Pit automated recovery system
 research
sonnet-ready
velocity-engine
Auto-generated by velocity engine
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
KimiClaw Rockachopa Timmy allegro antigravity bezalel claude claw-code codex-agent ezra gemini google grok hermes kimi manus perplexity sonnet
No Assignees bezalel
2 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Timmy_Foundation/timmy-config#343
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?