[BUG] CUDA Error: invalid device function /tmp/pip-req-build-5rlg4jgm/ln_fwd_kernels.cuh 236 about qwen HOT 4 CLOSED

Unfortunately, flash attention v2 does not support P100 (nor V100). You may need to uninstall the related packages in the image (pip uninstall flash_attn dropout_layer_norm) or build the image from scratch and set environment variable BUNDLE_FLASH_ATTENTION to false.

from qwen.

If you are using the provided the docker image with tag qwenllm/qwen(:latest), it is based on CUDA 11.7 and bundles the layer_norm module from flash attention v2, where that invalid device function (cudaOccupancyMaxActiveBlocksPerMultiprocessor which is a CUDA runtime API) is called.

It is likely your nvidia driver is too old to support CUDA 11.7 (and later versions). Please run nvidia-smi and provide the result.

from qwen.

If you are using the provided the docker image with tag qwenllm/qwen(:latest), it is based on CUDA 11.7 and bundles the layer_norm module from flash attention v2, where that invalid device function (cudaOccupancyMaxActiveBlocksPerMultiprocessor which is a CUDA runtime API) is called.

It is likely your nvidia driver is too old to support CUDA 11.7 (and later versions). Please run nvidia-smi and provide the result.

Wed Apr 10 06:16:11 2024
nvidia-smi驱动查询结果如下，感觉应该能支持CUDA11.7，有没有可能是别的什么原因呢
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 545.23.06 Driver Version: 545.23.06 CUDA Version: 12.3 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 Tesla P100-PCIE-16GB Off | 00000000:44:00.0 Off | 0 |
| N/A 27C P0 29W / 250W | 0MiB / 16384MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
| 1 Tesla P100-PCIE-16GB Off | 00000000:87:00.0 Off | 0 |
| N/A 27C P0 28W / 250W | 0MiB / 16384MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
| 2 Tesla P100-PCIE-16GB Off | 00000000:C1:00.0 Off | 0 |
| N/A 26C P0 30W / 250W | 0MiB / 16384MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
| 3 Tesla P100-PCIE-16GB Off | 00000000:C4:00.0 Off | 0 |
| N/A 26C P0 29W / 250W | 0MiB / 16384MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
| No running processes found |
+---------------------------------------------------------------------------------------+

from qwen.

Unfortunately, flash attention v2 does not support P100 (nor V100). You may need to uninstall the related packages in the image (pip uninstall flash_attn dropout_layer_norm) or build the image from scratch and set environment variable BUNDLE_FLASH_ATTENTION to false.

谢谢。

from qwen.