deadpipe

Results 10 comments of deadpipe

[Question] | ERROR | stderr | requests.exceptions.ConnectionError: HTTPConnectionPool(host='localhost', port=10000): Max retries exceeded with url: /refresh_all_workers (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f16ba0cb340>: Failed to establish a new connection: [Errno 111] Connection refused'))

hi am also facing the same problem have you found a solution? @gapjialin

[Question] | ERROR | stderr | requests.exceptions.ConnectionError: HTTPConnectionPool(host='localhost', port=10000): Max retries exceeded with url: /refresh_all_workers (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f16ba0cb340>: Failed to establish a new connection: [Errno 111] Connection refused'))

https://github.com/haotian-liu/LLaVA/issues/1230#issuecomment-2014765471 Temporary Fix

"Getting requirements to build wheel did not run successfully"

Facing same issue here. Have you found a solution, @mkloppel ?

How to accelerate inference?

@Maknee I tried setting option(MINIGPT4_CUBLAS "minigpt4: use cuBLAS" ON) in the [CMakeLists.txt](https://github.com/Maknee/minigpt4.cpp/blob/master/CMakeLists.txt#L35). But when i run cmake --build . --config Release, i get this error below unfortunately : - ![C__Windows_System32_cmd...

Unable to use GPU acceleration

@Maknee Do you have this on your roadmap to fix this CuBlas integration with minigpt4.cpp?

Error: Connection Refused by SGLANG Backend

> same problem @Z500-RAY have you found a solution?

Error: Connection Refused by SGLANG Backend

Has someone found a solution?

load_in_4bit works but load_in_8bit gives error : self and mat2 must have the same dtype, but got Half and Char

> > 4bit 模型是用cuda的算子来进行量化的，没有测试过8bit，可能是会出问题的 > > yes 4 bit is working but 8 bit giving error. > > I have tested cogvlm-chat-hf and it works in 8 bit same code...

How much VRAM required for Share Captioner?

@Han230104 So how much VRAM is actually being used in your A6000?

Zero Shot Classification on my own Dataset

So i have to create a new .py file which consists of my class or i should write another class within that file?