Skip to content

Instantly share code, notes, and snippets.

@FareedKhan-dev

FareedKhan-dev/sdpavssdpa_pages.md

Created July 4, 2025 07:36
Show Gist options
  • Save FareedKhan-dev/63fa61bf603a1726b997afebaecbe40d to your computer and use it in GitHub Desktop.
Save FareedKhan-dev/63fa61bf603a1726b997afebaecbe40d to your computer and use it in GitHub Desktop.
Download ZIP

Revisions

  1. FareedKhan-dev created this gist Jul 4, 2025.
    4 changes: 4 additions & 0 deletions sdpavssdpa_pages.md
    View file
    Original file line number Diff line number Diff line change
    @@ -0,0 +1,4 @@
    | Model Configuration | Avg. Latency (s) | Avg. Peak Memory (MB) | Avg. LLM Judge Score |
    | :----------------------- | :--------------- | :-------------------- | :------------------- |
    | **W4A16 + SDPA** | 1.103 | 1003.81 | 0.421 |
    | **W4A16 + SDPA Paged** | 1.303 | 1041.80 | 0.391 |