record current performance experiments

worklogs/remote_scripts/start_platform_245k_repro.sh

@@ -4,6 +4,8 @@ set -euo pipefail
 OUT="${1:-/root/work/logs/platform_245k_repro_20260715_01}"
 PORT="${PORT:-1111}"
 MODEL="${MODEL:-/root/public-storage/models/Qwen/Qwen3.6-35B-A3B}"
+MAX_NUM_BATCHED_TOKENS="${MAX_NUM_BATCHED_TOKENS:-16384}"
+MOE_DECODE_NATIVE="${MOE_DECODE_NATIVE:-0}"
 mkdir -p "$OUT"
 
 cd /root
@@ -18,7 +20,7 @@ export RMSNORM_NATIVE=1
 export LOOP1_NATIVE=1
 export PROF_TRACE=0
 export PROF_MOE_SUMMARY=0
-export MOE_DECODE_NATIVE=0
+export MOE_DECODE_NATIVE
 
 python3 - <<'PY'
 import os
@@ -55,6 +57,7 @@ print("sigkill_pids", left)
 PY
 
 echo "[repro] gpu before start" | tee "$OUT/driver.log"
+echo "[repro] MAX_NUM_BATCHED_TOKENS=$MAX_NUM_BATCHED_TOKENS MOE_DECODE_NATIVE=$MOE_DECODE_NATIVE" | tee -a "$OUT/driver.log"
 LD_LIBRARY_PATH=/usr/local/corex-3.2.3/lib64:/usr/local/corex/lib64:/usr/local/corex/lib:/usr/local/iluvatar/lib64 \
   /usr/local/corex/bin/ixsmi | tee -a "$OUT/driver.log"
 
@@ -71,7 +74,7 @@ nohup python3 -m vllm.entrypoints.openai.api_server \
   --max-num-seqs 1 \
   --disable-log-requests \
   --disable-frontend-multiprocessing \
-  --max-num-batched-tokens 16384 \
+  --max-num-batched-tokens "$MAX_NUM_BATCHED_TOKENS" \
   --enable-chunked-prefill \
   --max-seq-len-to-capture 245000 \
   --enable-auto-tool-choice \