mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 10:54:36 +00:00
metal : round up to 16 to fix MTLDebugComputeCommandEncoder assertion (#3938)
This commit is contained in:
parent
5ba3746171
commit
d9b33fe95b
@ -1017,7 +1017,7 @@ void ggml_metal_graph_compute(
|
|||||||
[encoder setBytes:&ne00 length:sizeof(ne00) atIndex:2];
|
[encoder setBytes:&ne00 length:sizeof(ne00) atIndex:2];
|
||||||
[encoder setBytes:&ne01 length:sizeof(ne01) atIndex:3];
|
[encoder setBytes:&ne01 length:sizeof(ne01) atIndex:3];
|
||||||
[encoder setBytes:&ne02 length:sizeof(ne02) atIndex:4];
|
[encoder setBytes:&ne02 length:sizeof(ne02) atIndex:4];
|
||||||
[encoder setThreadgroupMemoryLength:nth/32*sizeof(float) atIndex:0];
|
[encoder setThreadgroupMemoryLength:MAX(16, nth/32*sizeof(float)) atIndex:0];
|
||||||
|
|
||||||
[encoder dispatchThreadgroups:MTLSizeMake(ne01*ne02*ne03, 1, 1) threadsPerThreadgroup:MTLSizeMake(nth, 1, 1)];
|
[encoder dispatchThreadgroups:MTLSizeMake(ne01*ne02*ne03, 1, 1) threadsPerThreadgroup:MTLSizeMake(nth, 1, 1)];
|
||||||
} break;
|
} break;
|
||||||
@ -1348,7 +1348,7 @@ void ggml_metal_graph_compute(
|
|||||||
[encoder setBytes:&ne00 length:sizeof( int64_t) atIndex:2];
|
[encoder setBytes:&ne00 length:sizeof( int64_t) atIndex:2];
|
||||||
[encoder setBytes:&nb01 length:sizeof(uint64_t) atIndex:3];
|
[encoder setBytes:&nb01 length:sizeof(uint64_t) atIndex:3];
|
||||||
[encoder setBytes:&eps length:sizeof( float) atIndex:4];
|
[encoder setBytes:&eps length:sizeof( float) atIndex:4];
|
||||||
[encoder setThreadgroupMemoryLength:nth*sizeof(float) atIndex:0];
|
[encoder setThreadgroupMemoryLength:MAX(16, nth*sizeof(float)) atIndex:0];
|
||||||
|
|
||||||
const int64_t nrows = ggml_nrows(src0);
|
const int64_t nrows = ggml_nrows(src0);
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user