Add minimum capability requirement for AWQ #1064
Conversation
|
@WoosukKwon I think setup.py file might need add compute capability check whether to build quant kernel or not. |
|
@esmeetu Thanks for the suggestion! I've instead added a guard to prevent compilation for the supported GPUs. |
| namespace vllm { | ||
| namespace awq { |
There was a problem hiding this comment.
Why is this namespace needed?
There was a problem hiding this comment.
They are optional, but for better coding convention. From google cpp style guide:
With few exceptions, place code in a namespace.
Namespace prevents naming conflicts, so it's pretty useful for external code like the AWQ kernels.
| capability = torch.cuda.get_device_capability() | ||
| capability = capability[0] * 10 + capability[1] | ||
| if capability < quant_config.get_min_capability(): | ||
| raise ValueError( | ||
| f"The quantization method {model_config.quantization} is not " | ||
| "supported for the current GPU. " | ||
| f"Minimum capability: {quant_config.get_min_capability()}. " | ||
| f"Current capability: {capability}.") |
There was a problem hiding this comment.
Why do we need the assert false in C++ if we have the check here?
There was a problem hiding this comment.
Just saw the comments in the PR. Can we just change setup.py instead of the C++ files?
There was a problem hiding this comment.
It's problematic when we want to build the wheel for all GPU architectures (e.g., for pypi publication or building docker image). In such a case, we cannot selectively include the extension according to the architecture. Therefore, I believe this is an easier solution, and in fact we already used this kind of guard for bfloat16 attention kernels, which do not support Turing and Volta GPUs.
Closes #1063