Use TEP for Qwen H100 high concurrency

Author: anish-shanbhag

.github/configs/nvidia-master.yaml

@@ -9238,13 +9238,13 @@ qwen3.5-fp8-h100-sglang:
       search-space:
       - { tp: 8, ep: 1, conc-start: 1, conc-end: 8 }
       - { tp: 8, ep: 8, conc-start: 16, conc-end: 64 }
-      - { tp: 8, ep: 8, dp-attn: true, conc-start: 128, conc-end: 256 }
+      - { tp: 8, ep: 8, conc-start: 128, conc-end: 256 }
     - isl: 8192
       osl: 1024
       search-space:
       - { tp: 8, ep: 1, conc-start: 1, conc-end: 8 }
       - { tp: 8, ep: 8, conc-start: 16, conc-end: 64 }
-      - { tp: 8, ep: 8, dp-attn: true, conc-start: 128, conc-end: 256 }
+      - { tp: 8, ep: 8, conc-start: 128, conc-end: 256 }
 
 qwen3.5-fp8-h100-sglang-mtp:
   image: lmsysorg/sglang:v0.5.12-cu130

benchmarks/single_node/fixed_seq_len/qwen3.5_fp8_h100.sh

@@ -1,8 +1,7 @@
 #!/usr/bin/env bash
 
 # Qwen-3.5-397B-A17B FP8 on H100 via sglang.
-# Uses TP8/EP1 at conc 1-8, TP8/EP8 at conc 16-64,
-# and TP8/EP8 with DP attention at conc 128-256.
+# Uses TP8/EP1 at conc 1-8 and TP8/EP8 at conc 16-256.
 
 source "$(dirname "$0")/../../benchmark_lib.sh"
 
@@ -55,6 +54,9 @@ if [ "${DP_ATTENTION}" != "true" ]; then
       64)
         SCHEDULER_RECV_INTERVAL=600
         ;;
+      128|256)
+        SCHEDULER_RECV_INTERVAL=1920
+        ;;
       *)
         echo "Unsupported CONC=$CONC for qwen3.5 FP8 H100 SGLang recipe" >&2
         exit 1

perf-changelog.yaml

@@ -3456,7 +3456,7 @@
     - qwen3.5-fp8-h100-sglang
   description:
     - "Tune Qwen3.5-397B-A17B-FP8 H100 SGLang aggregate recipe for 1k/1k and 8k/1k sweeps"
-    - "Use TP8/EP1 for conc 1-8, TP8/EP8 for conc 16-64, and TP8/EP8 DP-attention for conc 128-256"
-    - "Use scheduler-recv-interval values 2/60/30/1200/600 for non-DP conc 1-4/8/16/32/64"
+    - "Use TP8/EP1 for conc 1-8 and TP8/EP8 for conc 16-256"
+    - "Use scheduler-recv-interval values 2/60/30/1200/600/1920 for conc 1-4/8/16/32/64/128-256"
     - "Set max-running-requests=256, chunked-prefill-size=16384, mem-fraction-static=0.8, cuda-graph-max-bs=CONC, and enable symm-mem"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1544