diff --git a/computility-run.yaml b/computility-run.yaml
index e17f30ff..f88472f5 100644
--- a/computility-run.yaml
+++ b/computility-run.yaml
@@ -8,16 +8,14 @@ command:
     - --served-model-name
     - llm
     - --max-model-len
-    - '256000'
+    - '100000'
     - --gpu-memory-utilization
-    - '0.95'
+    - '0.9'
     - --trust-remote-code
     - -tp
     - '4'
     - --max-num-seqs
-    - '2'
-    - --max-num-batched-tokens
-    - '4096'
+    - '1'
     - --disable-log-requests
     - --disable-frontend-multiprocessing
     - --enforce-eager
@@ -27,9 +25,8 @@ command:
     - --reasoning-parser
     - qwen3
     - --enable-prefix-caching
-    - --enable-chunked-prefill
     - --max-seq-len-to-capture
-    - '32768'
+    - '8192'
     - --dtype
     - half
 env:
diff --git a/qwen3_6_scripts/serving_chat.py b/qwen3_6_scripts/serving_chat.py
index 5461b3dd..b343a37b 100644
--- a/qwen3_6_scripts/serving_chat.py
+++ b/qwen3_6_scripts/serving_chat.py
@@ -247,11 +247,11 @@ class OpenAIServingChat(OpenAIServing):
             logger.exception("Error in loading multi-modal data")
             return self.create_error_response(str(e))
 
-        # Allow n≤2 (matches max_num_seqs=2 in computility-run.yaml).
-        # Sub168 passes t2_n_2 with HTTP 200.  Reject n>2 to prevent OOM.
+        # Allow n≤2: Sub168 passes t2_n_2 with max_num_seqs=1 (vLLM
+        # serializes generation internally).  Reject n>2 to prevent OOM.
         if request.n is not None and request.n > 2:
             logger.warning(
-                "n=%d rejected with 400 (exceeds max_num_seqs=2)", request.n)
+                "n=%d rejected with 400 (exceeds max supported value)", request.n)
             return self.create_error_response(
                 f"n={request.n} exceeds the maximum supported value of 2.")