From bda76cbd66f99fa4e75b0bcdaeffe954fcf68422 Mon Sep 17 00:00:00 2001 From: Mukesh Garg Date: Wed, 29 Jul 2026 14:14:24 -0700 Subject: [PATCH] =?UTF-8?q?analytical-viz:=20roofline=20tab=20=E2=80=94=20?= =?UTF-8?q?drop=20formula=20from=20step-latency=20header?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Revert the multi-line formula annotation on the 'Latency per decode step' header; make it a single-line markdown title matching the 'Cost per token' header on the right. Both headline plots now render at the same height so the plot area lines up. Co-Authored-By: Claude Opus 4.7 --- tests/analytical_visualization/app.py | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/tests/analytical_visualization/app.py b/tests/analytical_visualization/app.py index e5b6a97..56cc12d 100644 --- a/tests/analytical_visualization/app.py +++ b/tests/analytical_visualization/app.py @@ -2255,11 +2255,7 @@ with tab_roofline: # Plot A — Latency per decode step (undivided by B) with _hcol1: - st.markdown( - "**Latency per decode step** (one forward pass)\n\n" - "`t_step = N·b/W + 2·N·B/C + B·S_kv·kv_bpt/W`\n\n" - "` = weight_fetch + compute·B + KV_read·B`" - ) + st.markdown("**Latency per decode step** (one forward pass)") _figA, _axA = plt.subplots(figsize=(6, 4.2)) _axA.plot(_xs_head, [p.weight_s * 1e3 for p in _step_pts], "^-", color="#ffbe0b",