Sebastian Krüger
078043e35a
All checks were successful
Build and Push RunPod Docker Image / build-and-push (push) Successful in 14s
Adjusted VRAM allocation for concurrent operation: - Llama: 80% VRAM, 24576 context - BGE: 8% VRAM - Total: 88% of 24GB RTX 4090 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
11 lines
238 B
YAML
11 lines
238 B
YAML
model: meta-llama/Llama-3.1-8B-Instruct
|
|
host: "0.0.0.0"
|
|
port: 8001
|
|
uvicorn-log-level: "info"
|
|
gpu-memory-utilization: 0.80
|
|
max-model-len: 24576
|
|
dtype: auto
|
|
enforce-eager: false
|
|
enable-auto-tool-choice: true
|
|
tool-call-parser: "llama3_json"
|