Skip to content
#

model-flops-utilization

Star

Here are 4 public repositories matching this topic...

Language: All
Filter by language
All 4 Go 2 Python 2

Nathaniel-Alphonso / triadic-set-telemetry

Star 1

Public empirical record of the Triadic Set, a runtime governance architecture for the transformer forward pass. In-band constraint and restoration for LLM inference, with oracle-verified evaluation programs, engineered fixtures, exit-verdict instrumentation, and checksummed telemetry from 1B through 8B scale.

telemetry test-fixtures pre-registration inference-acceleration kv-cache llm-inference latency-reduction llm-evaluation compute-efficiency runtime-governance transformer-optimization confabulation-detection model-flops-utilization forward-hooks detector-evaluation tensor-interdiction single-turn-finality activation-density oracle-verification exit-gate
  • Updated Nov 10, 2026
  • Python

ehtishammubarik / truthscale

Star 0

Why is your GPU at 100% util but still slow? A zero-dependency Go CLI that diagnoses throttled, blocked, starved, or idle GPUs from DCGM + vLLM metrics — deterministic, replayable, and auditable.

kubernetes prometheus nvidia sre mfu gpu-monitoring finops gpu-utilization platform-engineering keda kv-cache inference-serving karpenter vllm llm-inference dcgm model-flops-utilization sm-occupancy gpu-fleet-management gpu-idle-detection
  • Updated Sep 4, 2026
  • Go

Add this topic to your repo

To associate your repository with the model-flops-utilization topic, visit your repo's landing page and select "manage topics."

Learn more