saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-30 20:18:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

[prefast:Warning]: C26409 ('PackedAttention<onnxruntime::MLFloat16>::TryGettingFusedRunner') (#15663)

Browse source 
### Description
<!-- Describe your changes. -->



### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
This commit is contained in:
Yufeng Li 2023-04-26 14:03:36 -07:00 committed by GitHub
parent 97c4cab6b7
commit d7ba9814cf
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
onnxruntime/contrib_ops/cuda/bert/packed_attention.cc
View file

@ -238,8 +238,8 @@ MHARunner* PackedAttention<T>::TryGettingFusedRunner(const PackedAttentionParame
// Assuming that num_heads and head_size do not change.
if (nullptr == fused_fp16_runner_.get()) {
fused_fp16_runner_.reset(new FusedMHARunnerFP16v2(num_heads_, parameters.head_size, sm, false /* causal_mask*/,
enable_trt_flash_attention_, parameters.scale));
fused_fp16_runner_ = FusedMHARunnerFP16v2::Create(num_heads_, parameters.head_size, sm, false /* causal_mask*/,
enable_trt_flash_attention_, parameters.scale);
}
// In case some kernel not loaded due to shared memory limit, we need to double check here.