|
|
a727526794
|
add length check to unwrap arguments
Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>
|
2026-02-12 15:31:50 +08:00 |
|
|
|
599957e156
|
support attention bwd
Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>
|
2026-02-10 17:01:28 +08:00 |
|
|
|
e41ec26329
|
support attention fwd
Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>
|
2026-02-09 17:15:51 +08:00 |
|
jinjieliu
|
213e4fc060
|
use templates to substitute parts of macros
Signed-off-by: jinjieliu <jinjie.liu@usc.edu>
|
2026-02-08 22:24:12 +08:00 |
|
jinjieliu
|
6a19a6b06d
|
put num_warps and num_stages in kwargs
Signed-off-by: jinjieliu <jinjie.liu@usc.edu>
|
2026-02-07 14:25:10 +08:00 |
|
jinjieliu
|
2298b6f8c8
|
support mm and autotune
Signed-off-by: jinjieliu <jinjie.liu@usc.edu>
|
2026-02-07 00:41:23 +08:00 |
|
|
|
f6c7a48c1b
|
enable lambda function for grid descriptor
Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>
|
2026-02-05 15:59:22 +08:00 |
|
jinjieliu
|
8b8aa6cb84
|
enable optional for numwarps and numstages
Signed-off-by: jinjieliu <jinjie.liu@usc.edu>
|
2026-02-05 01:01:49 +08:00 |
|
|
|
b7bf598fde
|
support softmax
Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>
|
2026-02-04 16:38:33 +08:00 |
|
|
|
192dc95ac0
|
supports decorator for jit and wrapper
Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>
|
2026-02-04 10:46:14 +08:00 |
|
jinjieliu
|
dc8c2c17e0
|
verify tvm-ffi cpp wrapper on vector-add.py
Signed-off-by: jinjieliu <jinjie.liu@usc.edu>
|
2026-02-04 02:36:06 +08:00 |
|