This commit is contained in:
2026-03-31 00:16:31 +08:00
parent 1a62b156ef
commit 24654096f1
3 changed files with 2 additions and 4 deletions
+1 -2
View File
@@ -1,5 +1,4 @@
# FROM docker.1ms.run/vllm/vllm-openai-rocm:latest
FROM vllm/vllm-openai-rocm:nightly
FROM vllm/vllm-openai-rocm:latest
WORKDIR /workspace
+1 -1
View File
@@ -124,7 +124,7 @@ curl -X POST "http://localhost:8001/v1/chat/completions" \
## 常见故障排查
- 报错 `Model architectures ['Qwen3_5MoeForConditionalGeneration'] are not supported for now` 时,在对应 profile 增加 `model_impl=transformers`,并使用当前 Dockerfile 重建镜像后再启动。
- 报错 `Model architectures ['Qwen3_5MoeForConditionalGeneration'] are not supported for now` 或 `The Transformers implementation ... is not compatible with vLLM` 时,说明当前 vLLM 栈与该模型架构不兼容,需切换到兼容模型或改用其他推理后端。
- 报错 `model config (gptq) does not match quantization argument (gptq_marlin)` 时,将该模型配置改为 `dtype=float16` 且 `quantization=gptq`。
- 报错 `RPC call to sample_tokens timed out` 或出现 `GPU core dump` 时,先下调模型配置为更稳参数:`ctx=32768`、`max_num_seqs=4`、`max_tokens=2048`、`gpu_util=0.90`,并开启 `enforce_eager=true`。
- 若模型目录存在但仍加载失败,检查挂载路径是否为 `/opt/model:/opt/model:ro`,并确认容器内可见模型文件。
-1
View File
@@ -73,7 +73,6 @@
"local_path": "Qwen3.5-35B-A3B-GPTQ-Int4",
"dtype": "float16",
"quantization": "moe_wna16",
"model_impl": "transformers",
"ctx": "32768",
"trust_remote": true,
"valid_tp": [1, 2],