From 7f16b711a749b3fe656b737ce182d5b952bb719f Mon Sep 17 00:00:00 2001
From: root <root@qpmriflz.colocrossing.cloud>
Date: Wed, 2 Sep 2026 02:44:22 +0000
Subject: [PATCH] fix yaml

---
 computility-run.yaml | 71 ++++++++++++++++++++++++--------------------
 1 file changed, 38 insertions(+), 33 deletions(-)

diff --git a/computility-run.yaml b/computility-run.yaml
index 178a4876..da12e930 100644
--- a/computility-run.yaml
+++ b/computility-run.yaml
@@ -1,48 +1,53 @@
 concurrency: 1
 command:
-    - bash
-    - -c
-    - >-
-        python3 /workspace/qwen3_6_scripts/patch_chat_template.py /model 2>&1 || echo '[runtime] chat template patch failed';
-        exec python3 -m vllm.entrypoints.openai.api_server
-        --model /model
-        --served-model-name llm
-        --max-model-len 131072
-        --gpu-memory-utilization 0.92
-        --trust-remote-code
-        -tp 4
-        --max-num-seqs 2
-        --disable-log-requests
-        --disable-frontend-multiprocessing
-        --max-num-batched-tokens 4096
-        --enable-chunked-prefill
-        --max-seq-len-to-capture 32768
-        --enable-auto-tool-choice
-        --tool-call-parser qwen3_coder
-        --reasoning-parser qwen3
-        --enable-prefix-caching
-        --enforce-eager
-        --dtype half
+    - python3
+    - -m
+    - vllm.entrypoints.openai.api_server
+    - --model
+    - /model
+    - --served-model-name
+    - llm
+    - --max-model-len
+    - '131072'
+    - --gpu-memory-utilization
+    - '0.92'
+    - --trust-remote-code
+    - -tp
+    - '4'
+    - --max-num-seqs
+    - '2'
+    - --disable-log-requests
+    - --disable-frontend-multiprocessing
+    - --max-num-batched-tokens
+    - '4096'
+    - --enable-chunked-prefill
+    - --max-seq-len-to-capture
+    - '32768'
+    - --enable-auto-tool-choice
+    - --tool-call-parser
+    - qwen3_coder
+    - --reasoning-parser
+    - qwen3
+    - --enable-prefix-caching
+    - --enforce-eager
+    - --dtype
+    - half
 env:
     - name: VLLM_ENGINE_ITERATION_TIMEOUT_S
-      value: '3600'
+      value: 3600
     - name: BI100_MAX_NUM_SEQS
-      value: '2'
-    # --- MoE kernel selection ---
+      value: 2
     - name: BI100_MOE_COREX_DIRECT_ROUTED
-      value: '1'
+      value: 1
     - name: BI100_MOE_COREX_TOPK_SOFTMAX
-      value: '1'
-    # --- GDN kernel selection ---
+      value: 1
     - name: BI100_GDN_COREX_PACKED_DECODE
-      value: '1'
-    # --- Hybrid KV/GDN cache ---
+      value: 1
     - name: BI100_HYBRID_KV_ACCOUNTING
       value: full_attention
     - name: BI100_GDN_CACHE_POLICY
       value: admission64
     - name: BI100_GDN_RESTORE_MODE
       value: hybrid64
-    # --- Image fetch timeout (container network) ---
     - name: VLLM_IMAGE_FETCH_TIMEOUT
-      value: '10'
\ No newline at end of file
+      value: 10
\ No newline at end of file