remove allreduce fusion arg

Author: Ankur-singh

.github/configs/nvidia-master.yaml

@@ -1804,6 +1804,31 @@ qwen3.5-bf16-b200-sglang:
     search-space:
     - { tp: 8, ep: 1, conc-start: 4, conc-end: 64 }
 
+qwen3.5-fp8-b200-sglang:
+  image: lmsysorg/sglang:v0.5.9-cu129-amd64
+  model: Qwen/Qwen3.5-397B-A17B-FP8
+  model-prefix: qwen3.5
+  runner: b200
+  precision: fp8
+  framework: sglang
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 4, ep: 4, conc-start: 4, conc-end: 16 }
+    - { tp: 4, ep: 4, conc-start: 64, conc-end: 64 }
+  - isl: 1024
+    osl: 8192
+    search-space:
+    - { tp: 8, ep: 1, conc-start: 4, conc-end: 8 }
+    - { tp: 4, ep: 4, conc-start: 8, conc-end: 64}
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 8, ep: 1, conc-start: 4, conc-end: 4}
+    - { tp: 4, ep: 4, conc-start: 8, conc-end: 64 }
+
 qwen3.5-fp4-b200-sglang:
   image: lmsysorg/sglang:v0.5.9-cu129-amd64
   model: nvidia/Qwen3.5-397B-A17B-NVFP4

benchmarks/single_node/qwen3.5_fp4_b200.sh

@@ -42,7 +42,7 @@ PYTHONNOUSERSITE=1 python3 -m sglang.launch_server --model-path=$MODEL --host=0.
 --mem-fraction-static $MEM_FRAC_STATIC --chunked-prefill-size 32768 --max-prefill-tokens 32768 \
 --context-length $CONTEXT_LENGTH --disable-radix-cache \
 --attention-backend trtllm_mha --moe-runner-backend flashinfer_trtllm \
---enable-flashinfer-allreduce-fusion --scheduler-recv-interval 30 \
+--scheduler-recv-interval 30 \
 --stream-interval 30 --quantization modelopt_fp4 \
 --kv-cache-dtype fp8_e4m3 --fp4-gemm-backend flashinfer_cutlass > $SERVER_LOG 2>&1 &