Gemm fp8 run error - Githubissues

microsoft / onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

https://onnxruntime.ai

MIT License

13.51k stars 2.76k forks source link

Gemm fp8 run error #20869

Open KnightYao opened 1 month ago

KnightYao commented 1 month ago

Describe the issue

when i use gemm_float8 to run with input A(fp8 e5m2), input B(fp8 e4m3), can not run, but input A(fp8 e4m3), input B(fp8 e4m3) will run right,

To reproduce

run gemm_float8

Urgency

No response

Platform

Linux

OS Version

centos7.6

ONNX Runtime Installation

Built from Source

ONNX Runtime Version or Commit ID

1.17.1

ONNX Runtime API

Python

Architecture

X64

Execution Provider

CUDA

Execution Provider Library Version

cuda 12.1

xadupre commented 1 month ago

Can you be more explicit about the error message you get?

KnightYao commented 1 month ago

https://github.com/microsoft/onnxruntime/pull/20911

KnightYao commented 1 month ago

Can you be more explicit about the error message you get?

I have fix this bug https://github.com/microsoft/onnxruntime/pull/20911

github-actions[bot] commented 4 days ago

This issue has been automatically marked as stale due to inactivity and will be closed in 30 days if no further activity occurs. If further support is needed, please provide an update and/or more details.