Merge pull request #44 from suppathak/compressed-models

Added a nb demonstrating efficient gpu utilizations
redhat-et · Mar 22, 2024 · 48db5dc · 48db5dc
2 parents 1a04c8a + bdf592e
commit 48db5dc
Show file tree

Hide file tree

Showing 3 changed files with 528 additions and 0 deletions.
diff --git a/notebooks/efficient-gpu-utilization.ipynb b/notebooks/efficient-gpu-utilization.ipynb
diff --git a/reports/figures/LLM_size.png b/reports/figures/LLM_size.png
diff --git a/reports/figures/llm_int8.png b/reports/figures/llm_int8.png