Spaces:
Runtime error
Runtime error
Commit History
-
Initial commit: LLM Inference Dashboard
A production-grade Gradio dashboard for monitoring vLLM inference on multi-GPU setups with: - GPU/Rank monitoring (memory, utilization, temperature) - Inference metrics (tokens/sec, TTFT, KV cache) - Quantization detection (GPTQ, AWQ, bitsandbytes) - Model loading progress tracking - Alerting with Slack/webhook integration - Request tracing with latency breakdown - A/B deployment comparison - Built-in load testing Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>aefabf0