diff --git a/computility-run.yaml b/computility-run.yaml
index 9fd7ac4d..c6a03f5b 100644
--- a/computility-run.yaml
+++ b/computility-run.yaml
@@ -8,18 +8,18 @@ command:
     - --served-model-name
     - llm
     - --max-model-len
-    - '256000'
+    - '131072'
     - --gpu-memory-utilization
-    - '0.95'
+    - '0.90'
     - --trust-remote-code
     - -tp
     - '4'
     - --max-num-seqs
-    - '2'
+    - '1'
     - --disable-log-requests
     - --disable-frontend-multiprocessing
     - --max-num-batched-tokens
-    - '4096'
+    - '8192'
     - --enable-chunked-prefill
     - --max-seq-len-to-capture
     - '32768'
@@ -45,3 +45,5 @@ env:
       value: admission64
     - name: BI100_GDN_RESTORE_MODE
       value: hybrid64
+    - name: BI100_MOE_COREX_TOPK_SOFTMAX
+      value: '0'