PaddlePaddle / PaddlePaddle/FastDeploy
FastDeploy完整启动代码 ， fastdeploy.entrypoints.openai.api_server
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.7k
- Forks
- 756
- Avg merge
- 19h 28m
- Merged PRs (30d)
- 4
Description
使用下面的启动命令：
命令1：
python -m fastdeploy.entrypoints.openai.api_server
--model Qwen/Qwen3-0.6B
--port 8180
--metrics-port 8181
--engine-worker-queue-port 8182
--max-model-len 8192
--max-num-seqs 4
--load_choices "default_v1"
命令2：
python -m fastdeploy.entrypoints.openai.api_server
--model baidu/ERNIE-4.5-0.3B-Paddle
--port 8180
--metrics-port 8181
--engine-worker-queue-port 8182
--max-model-len 8192
--max-num-seqs 4
都出现加载模型权重错误，报错如下：
ValueError: (InvalidArgument) matmul(): argument 'x' (position 0) must be Tensor, but got list (at /paddle/paddle/fluid/pybind/eager_utils.cc:1508)
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Reproduce the failure with the commands in the issue using fastdeploy.entrypoints.openai.api_server. Start by tracing model loading from that entry point and inspect where the reported matmul call receives a list instead of a Tensor. Done means both listed model commands load successfully and the API server starts without this error.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- api, backend
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100