ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Add some minimal optimizations for CDNA (#10498)

Browse source 
* Add some minimal optimizations for CDNA

* ggml_cuda: set launch bounds also for GCN as it helps there too
This commit is contained in:
uvos 2024-11-27 17:10:08 +01:00 • committed by GitHub
parent 46c69e0e75
commit 3ad5451f3b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 36 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml/src/ggml-cuda/mmq.cu
View file

@ -148,5 +148,5 @@ bool ggml_cuda_should_use_mmq(enum ggml_type type, int cc, int64_t ne11) {
return cc < CC_VOLTA || ne11 < MMQ_DP4A_MAX_BATCH_SIZE;
}
return cc < CC_RDNA3 || ne11 < MMQ_DP4A_MAX_BATCH_SIZE;
return (cc < CC_RDNA3 && cc != CC_CDNA && cc != CC_VEGA20) || ne11 < MMQ_DP4A_MAX_BATCH_SIZE;
}