From 7bc53e74307747fa0a74876047845e4bcc5d5296 Mon Sep 17 00:00:00 2001 From: lishunyang12 Date: Wed, 15 Jul 2026 10:03:19 +0000 Subject: [PATCH] docs: drop calibration intro paragraph --- docs/design/skip_softmax_sage_trtllm_gen.md | 2 -- 1 file changed, 2 deletions(-) diff --git a/docs/design/skip_softmax_sage_trtllm_gen.md b/docs/design/skip_softmax_sage_trtllm_gen.md index 1e3cc4a0a..5e6e6caf6 100644 --- a/docs/design/skip_softmax_sage_trtllm_gen.md +++ b/docs/design/skip_softmax_sage_trtllm_gen.md @@ -77,8 +77,6 @@ Env var = flag in UPPER_SNAKE (e.g. `TRTLLM_GEN_SAGE=1`). ### ModelOpt skip calibration -Sweep `target_sparsity`, fit `factor = a·exp(b·target_sparsity)` per `config_group` → `config.json`. Steps 2–3 fix `target_sparsity`, sweep **D = `disabled_until_timestep`** (1.00 = off → 0.94 = most aggressive). D is a runtime gate, not calibrated. - **Setup** (per model) | Model | calib prompts | # samples | res / frames | config_groups | ignore layers |