paper(figures): GQA long-context decode 4-cases comparative figures

Browse Source

Generated by scripts/paper/paper_plot_gqa_decode_long_ctx_4cases.py
from the bench's sweep.json (S_kv=8192, the headline 128K run was
sidestepped — Case 2's single-PE 128-tile sweep is the long pole
and shape/ordering is preserved across scales).

  gqa_decode_long_ctx_4cases_latency.png   end-to-end latency / case
  gqa_decode_long_ctx_4cases_traffic.png   ipcq / dma op-count breakdown
  gqa_decode_long_ctx_4cases_memory.png    KV bytes per cube (slide-11)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

...

This commit is contained in:

Mukesh Garg

2026-06-15 17:48:34 -07:00

parent 1fbe833992

commit 7c346dec1b

3 changed files with 0 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

docs/report/1H-codesign-paper/figures/gqa_decode_long_ctx_4cases_latency.png

BIN

Binary file not shown.

Side by Side After Width:  |  Height:  |  Size: 47 KiB

docs/report/1H-codesign-paper/figures/gqa_decode_long_ctx_4cases_memory.png

BIN

Binary file not shown.

Side by Side After Width:  |  Height:  |  Size: 42 KiB

docs/report/1H-codesign-paper/figures/gqa_decode_long_ctx_4cases_traffic.png

BIN

Binary file not shown.

Side by Side After Width:  |  Height:  |  Size: 41 KiB