mirror of
				https://github.com/ggml-org/llama.cpp.git
				synced 2025-10-31 08:51:55 +00:00 
			
		
		
		
	musa: override warp_size of musa device to 32 (#12445)
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
This commit is contained in:
		| @@ -262,6 +262,8 @@ static ggml_cuda_device_info ggml_cuda_init() { | ||||
|                       id, prop.name, prop.gcnArchName, info.devices[id].cc & 0xffff, | ||||
|                       device_vmm ? "yes" : "no", prop.warpSize); | ||||
| #elif defined(GGML_USE_MUSA) | ||||
|         // FIXME: Ensure compatibility with varying warp sizes across different MUSA archs. | ||||
|         info.devices[id].warp_size = 32; | ||||
|         // TODO: refine the .cc to reflect MUSA's actual CC capabilities | ||||
|         info.devices[id].smpbo = prop.sharedMemPerBlockOptin; | ||||
|         info.devices[id].cc = 100*prop.major + 10*prop.minor; | ||||
|   | ||||
		Reference in New Issue
	
	Block a user
	 R0CKSTAR
					R0CKSTAR