From 9cca2c60c97ae1eec698e7b38c38ef52bc7e7d65 Mon Sep 17 00:00:00 2001
From: Claude Code Agent <VtimothyeveeE@europe.com>
Date: Wed, 13 May 2026 15:31:40 +0800
Subject: [PATCH] feat(experiments): expose PREFILL_MEM_FRAC + plumb
 --prefill-mem-fraction-static

v7 with --decode-mem-fraction-static=0.8 + SGLANG_SNAPSHOT_LINK_BUF_BYTES=16GB
silently fell back to 1 GB snapshot_buf because Prefill (mem-fraction
default 0.88) left only 10.8 GB free on GPU 0. Reducing prefill
mem-fraction lets 16 GB snapshot_buf fit.
---
 scripts/sweep_e4_pressured.sh | 1 +
 1 file changed, 1 insertion(+)

diff --git a/scripts/sweep_e4_pressured.sh b/scripts/sweep_e4_pressured.sh
index 605817c..85d6a65 100755
--- a/scripts/sweep_e4_pressured.sh
+++ b/scripts/sweep_e4_pressured.sh
@@ -104,6 +104,7 @@ uv run --no-sync python -m agentic_pd_hybrid.cli benchmark-live \
   --kvcache-direct-max-uncached-tokens 8192 \
   --kvcache-load-floor-bonus "$LOAD_FLOOR_BONUS" \
   --decode-mem-fraction-static "${DECODE_MEM_FRAC:-0.4}" \
+  --prefill-mem-fraction-static "${PREFILL_MEM_FRAC:-0.7}" \
   --enable-d-to-p-sync 2>&1 | tee -a "$LOG"
 
 run_dir=$(ls -td "$OUTPUT"/kvcache-centric-*/ 2>/dev/null | head -1)