Commit graph

4 commits

Author SHA1 Message Date
Satya Kumar Jandhyala
bab5037eab
Eliminate explicit Concat operations in Attention (#20556)
### Description
Remove explicitly concatinating pastKey with Key and pastValue with
Value.



### 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. -->
2024-05-24 09:07:57 -07:00
Satya Kumar Jandhyala
21b3cbc3af
[WIP][JS/WebGPU] Inputs Key and Value could be 4-dims. (#20470)
### Description
The Key and Value inputs could be 4-dims


### 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. -->
2024-04-25 13:33:46 -07:00
Satya Kumar Jandhyala
ae78cdb5d7
[JS/WebGPU] MultiheadAttention bugfix (#20447)
### Description
Fixed pastkey, key and pastvalue, value concatenation condition and
fixed index error. Added new test cases.



### 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. -->
2024-04-24 08:43:14 -07:00
Satya Kumar Jandhyala
d42ac7f0c6
[JS/WebGPU] Multihead attention improvements (#20286)
### Description
Enabled more usecases



### 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. -->
2024-04-23 12:39:49 -07:00
Renamed from js/web/test/data/ops/multi-head-attention.jsonc (Browse further)