Update GPTOSS B200 TRTLLM (#266)

* Update GPTOSS B200 AGG

* set dp attention env vars

* Add DP attn comment

---------

Co-authored-by: Jatin Gangani <jgangani@dc2-container-xterm-014.prd.it.nvidia.com>

Author: jgangani

.github/configs/nvidia-master.yaml

@@ -167,34 +167,38 @@ dsr1-fp8-h200-trt:
     - { tp: 8, ep: 8, dp-attn: true, conc-start: 64, conc-end: 64 }
 
 gptoss-fp4-b200-trt:
-  image: nvcr.io#nvidia/tensorrt-llm/release:1.2.0rc0.post1
+  image: nvcr.io#nvidia/tensorrt-llm/release:1.2.0rc2
   model: openai/gpt-oss-120b
   model-prefix: gptoss
   runner: b200-trt
   precision: fp4
   framework: trt
-  # For all sequence lengths, if CONC >= 256, then EP=TP and DP_ATTN=true
+  # Enable DP_ATTENTION for conc >= 32
   seq-len-configs:
   - isl: 1024
     osl: 1024
     search-space:
+    - { tp: 2, dp-attn: true, conc-start: 32, conc-end: 128 }
+    - { tp: 4, dp-attn: true, conc-start: 32, conc-end: 64 }
     - { tp: 1, conc-start: 64, conc-end: 128 }
-    - { tp: 2, conc-start: 4, conc-end: 128 }
-    - { tp: 4, conc-start: 4, conc-end: 128 }
+    - { tp: 2, conc-start: 4, conc-end: 32 }
+    - { tp: 4, conc-start: 4, conc-end: 64 }
     - { tp: 8, conc-start: 4, conc-end: 8 }
   - isl: 1024
     osl: 8192
     search-space:
     - { tp: 1, conc-start: 64, conc-end: 128 }
+    - { tp: 2, dp-attn: true, conc-start: 64, conc-end: 128 }
     - { tp: 2, conc-start: 4, conc-end: 128 }
     - { tp: 4, conc-start: 4, conc-end: 128 }
     - { tp: 8, conc-start: 4, conc-end: 16 }
   - isl: 8192
     osl: 1024
     search-space:
     - { tp: 1, conc-start: 64, conc-end: 128 }
+    - { tp: 2, dp-attn: true, conc-start: 64, conc-end: 128 }
     - { tp: 2, conc-start: 4, conc-end: 128 }
-    - { tp: 4, conc-start: 4, conc-end: 128 }
+    - { tp: 4, conc-start: 4, conc-end: 32 }
     - { tp: 8, conc-start: 4, conc-end: 8 }
 
 gptoss-fp4-b200-vllm:

benchmarks/gptoss_fp4_b200_trt_slurm.sh

@@ -31,7 +31,6 @@ echo "MOE_BACKEND set to '$MOE_BACKEND'"
 
 EXTRA_CONFIG_FILE="gptoss-fp4.yml"
 export TRTLLM_ENABLE_PDL=1
-export NCCL_GRAPH_REGISTER=0
 
 cat > $EXTRA_CONFIG_FILE << EOF
 cuda_graph_config:
@@ -50,6 +49,9 @@ moe_config:
 EOF
 
 if [[ "$DP_ATTENTION" == "true" ]]; then
+    export TRTLLM_MOE_ALLTOALL_BACKEND="mnnvlthroughput"
+    export TRTLLM_FORCE_ALLTOALL_METHOD="MNNVL"
+    export TRTLLM_MOE_A2A_WORKSPACE_MB="2048"
     cat << EOF >> $EXTRA_CONFIG_FILE
 attention_dp_config:
     enable_balance: true