x

2026-03-29 04:40:36 +08:00
parent acd5ed518e
commit 3d88c2f416
2 changed files with 7 additions and 0 deletions
@@ -106,6 +106,7 @@
      "max_num_seqs": "64",
      "max_tokens": "32768",
      "gpu_util": "0.98",
+      "model_impl": "transformers",
      "tool_call_parser": "qwen3_xml",
      "enable_auto_tool_choice": true,
      "served_model_name": "Qwen3.5-27B-FP8",
@@ -118,6 +119,7 @@
      "max_num_seqs": "64",
      "max_tokens": "32768",
      "gpu_util": "0.98",
+      "model_impl": "transformers",
      "tool_call_parser": "qwen3_xml",
      "enable_auto_tool_choice": true,
      "served_model_name": "Qwen3.5-35B-A3B-GPTQ-Int4",
@@ -144,6 +144,11 @@ def launch_model(model_id, config, model_path, gpu_count):
        "--gpu-memory-utilization", str(gpu_util),
        "--dtype", "auto"
    ]
+
+    model_impl = config.get("model_impl") or os.getenv("VLLM_MODEL_IMPL")
+    if model_impl:
+        cmd.extend(["--model-impl", str(model_impl)])
+        log(f"Added model implementation: {model_impl}")
    
    if config.get("trust_remote"):
        cmd.append("--trust-remote-code")