enable all configs

Author: Jatin Gangani

.github/workflows/benchmark-multinode-tmpl.yml

@@ -102,7 +102,6 @@ jobs:
               prefill_gpus=$(echo "$result_file" | sed -n "s/.*_ctx-\([0-9]*\).*\.json/\1/p")
               decode_gpus=$(echo "$result_file" | sed -n "s/.*_gen-\([0-9]*\).*\.json/\1/p")
               
-              echo "Extracted: gpus=$gpus, prefill_gpus=$prefill_gpus, decode_gpus=$decode_gpus"
               if [ -n "$gpus" ]; then
                 echo "Extracted: gpus=$gpus, prefill_gpus=$prefill_gpus, decode_gpus=$decode_gpus"
                 TP=$gpus RESULT_FILENAME=${result_file%.json} EP_SIZE=1 DP_ATTENTION=false PREFILL_GPUS="$prefill_gpus" DECODE_GPUS="$decode_gpus" python3 utils/process_result.py

runners/launch_gb200-nv.sh

@@ -113,11 +113,11 @@ if [[ $FRAMEWORK == "dynamo-trtllm" ]]; then
 
                     echo "Running 8k/1k MTP=OFF configurations for GPT-OSS"
 
-                    #./submit_disagg.sh mtp=off tp 1 1 1 512 20000 "0.9" 0 0 "128 256 512"
-                    #./submit_disagg.sh mtp=off tp 1 1 2 1024 20000 "0.9" 0 0 "64 128 256"
-                    ./submit_disagg.sh mtp=off tep 1 1 2 1024 20000 "0.9" 0 0 "64" #"64 256"
-                    #./submit_disagg.sh mtp=off tp 1 1 4 2048 20000 "0.9" 0 0 "8 16 32 64 128"
-                    #./submit_disagg.sh mtp=off tp 1 1 8 2048 20000 "0.9" 0 0 "1 2 4 8 16"
+                    ./submit_disagg.sh mtp=off tp 1 1 1 512 20000 "0.9" 0 0 "128 256 512"
+                    ./submit_disagg.sh mtp=off tp 1 1 2 1024 20000 "0.9" 0 0 "64 128 256"
+                    ./submit_disagg.sh mtp=off tep 1 1 2 1024 20000 "0.9" 0 0 "64 256"
+                    ./submit_disagg.sh mtp=off tp 1 1 4 2048 20000 "0.9" 0 0 "8 16 32 64 128"
+                    ./submit_disagg.sh mtp=off tp 1 1 8 2048 20000 "0.9" 0 0 "1 2 4 8 16"
             else
                 echo "Unsupported ISL/OSL combination for GPT-OSS: $isl/$osl"
                 exit 1