x

config.json

@@ -20,7 +20,7 @@
   "revision": "",
   "models": {
     "default": "Qwen3.5-35B-A3B-GPTQ-Int4",
-    "selected": "Qwen3.6-27B-FP8",
+    "selected": "Qwen3.6-35B-A3B-FP8",
     "profiles": {
       "Qwen3.6-35B-A3B-FP8": {
         "local_path": "Qwen3.6-35B-A3B-FP8",
@@ -28,14 +28,14 @@
         "quantization": "fp8",
         "ctx": "262144",
         "max_tokens": "65536",
-        "max_num_batched_tokens": 16384,
+        "max_num_batched_tokens": 32768,
         "trust_remote": true,
         "enforce_eager": false,
         "valid_tp": [
           2
         ],
-        "max_num_seqs": "12",
-        "gpu_util": "0.90",
+        "max_num_seqs": "256",
+        "gpu_util": "0.92",
         "tool_call_parser": "qwen3_coder",
         "reasoning_parser": "qwen3",
         "enable_auto_tool_choice": true,
@@ -69,18 +69,19 @@
         "local_path": "Qwen3.6-27B-FP8",
         "dtype": "auto",
         "quantization": "fp8",
-        "ctx": "32768",
-        "max_tokens": "16384",
-        "max_num_batched_tokens": 8192,
+        "ctx": "262144",
+        "max_tokens": "65536",
+        "max_num_batched_tokens": 32768,
         "trust_remote": true,
         "enforce_eager": false,
         "valid_tp": [
+          1,
           2
         ],
-        "max_num_seqs": 16,
-        "gpu_util": "0.80",
+        "max_num_seqs": 256,
+        "gpu_util": "0.92",
         "kv_cache_dtype": "fp8",
-        "enable_prefix_caching": false,
+        "enable_prefix_caching": true,
         "tool_call_parser": "qwen3_coder",
         "reasoning_parser": "qwen3",
         "enable_auto_tool_choice": true,