Dung M. Dao

icon indicating a website link https://dungminhdao.github.io/ icon indicating an email [email protected]

icon company @SOICTInnovationClub icon location Hanoi, Vietnam icon location AI Resident at FPT Software AI Center

Results 6 comments of Dung M. Dao

[bugfix] Fix persisted chromadb vectorstore

@hwchase17 This issue is still there in `0.0.171`

C++ Version of Qwen-VL?

Same question here

Inference with GPU took too much GPU RAM

Thanks for replying. I don't know but somehow it still uses 34GB even when I switched to the `fp16` branch of the HuggingFace model weights you linked to, and I...

Inference super slow

I guess you can try inference with GPU, after making some modifications to the code: ```python llama/memory_pool.py: self.sess = ort.InferenceSession(onnxfile, providers=['CUDAExecutionProvider']) ``` Find all the files with `import onnxruntime` and...

Inference super slow

> I am struggling to get it to run, did you already make it run? Could you please tell me how many tokens/second you get out of the 7b or...

[BUG] Get corrupted ROSBAG file when running ROSBAG Recording code sample

> Hi, can you provide information about the size of files? Sure, the file size is 1.9 GB and recorded for about 25 seconds