[WebNN EP] Support GroupQueryAttention(GQA) #23416
peishenyan
force pushed
from
cc00695e
to
03c0a1e1
345 days ago
peishenyan
force pushed
from
03c0a1e1
to
e853f5e1
345 days ago
peishenyan
force pushed
from
e853f5e1
to
537daa0a
342 days ago
peishenyan
force pushed
from
9a8a61a9
to
203a7c78
322 days ago
peishenyan
force pushed
from
203a7c78
to
9c4b8316
314 days ago
peishenyan
force pushed
from
9c4b8316
to
8e340413
310 days ago
peishenyan
force pushed
from
467e91e4
to
e96cd008
296 days ago
peishenyan
force pushed
from
e96cd008
to
7e5b61e6
296 days ago
peishenyan
marked this pull request as ready for review 294 days ago
Honry
commented
on 2025-03-10
peishenyan
force pushed
from
2a0b1dbd
to
2610aaaa
287 days ago
peishenyan
force pushed
from
ca367388
to
2061b616
286 days ago
peishenyan
force pushed
from
b2daa1b9
to
c63b6030
285 days ago
peishenyan
force pushed
from
7837e2d4
to
b6ef306c
282 days ago
peishenyan
force pushed
from
b6ef306c
to
1b20aab4
282 days ago
peishenyan
force pushed
from
1b20aab4
to
9d6cdeef
282 days ago
peishenyan
force pushed
from
9d6cdeef
to
248f6cef
282 days ago
peishenyan
force pushed
from
248f6cef
to
9e280e2d
282 days ago
peishenyan
force pushed
from
160dfc71
to
0f1b31e0
282 days ago
peishenyan
force pushed
from
0f1b31e0
to
5903bcf7
280 days ago
peishenyan
force pushed
from
5903bcf7
to
0ee16b67
280 days ago
peishenyan
force pushed
from
0ee16b67
to
db329549
273 days ago
peishenyan
force pushed
from
db329549
to
bb3d6117
273 days ago
peishenyan
force pushed
from
bb3d6117
to
9430d6fc
273 days ago
Honry
commented
on 2025-03-21
fdwr
commented
on 2025-04-07
fdwr
commented
on 2025-04-07
fdwr
dismissed these changes
on 2025-04-07
peishenyan
dismissed their stale review
via 7cb848ff
265 days ago
peishenyan
force pushed
from
41c334aa
to
7cb848ff
265 days ago
fdwr
dismissed these changes
on 2025-04-07
simple implementation for GQA
e7ca7d6d
add input and output cast when fp16
9bcb2e91
add comments
a80234e8
add support for group query
336dde4b
format code
637a4232
fix kv_num_heads bugs
817af747
fix wrong variable name
82b20831
fix bugs
4f76e5e4
fix reshape bugs
9bc2f4e9
skip total_sequence_length input for GQA op
c447c958
temp
6c75da1c
address comments and improve shape inference for GQA
42d8dc82
add constant creator for given array
1cb00da0
address comments
163ed971
update matMulNBits_op_builder.cc and remove unused header file
9b01f362
peishenyan
dismissed their stale review
via 9b01f362
263 days ago
peishenyan
force pushed
from
7cb848ff
to
9b01f362
263 days ago
fdwr
approved these changes
on 2025-04-10
fdwr
merged
f12a89e9
into main 262 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub