diff options
| author | JidongZhang-THU <1119708529@qq.com> | 2024-01-31 21:10:15 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-01-31 15:10:15 +0200 |
| commit | 15606309a05ccf7fadbaad5538cb7c32acb1e06b (patch) | |
| tree | aae8b8e0977922438c1e514e961f7c8bea2dcb9a /common/common.cpp | |
| parent | b2b9f025e7821e78bd501d75d01838c26de07a57 (diff) | |
llava : add MobileVLM support (#5132)
* New Feature:
1. Sum_Rows:
fix cuda kernel overflow
fix block shape error when nrows too big
2. Im2Col:
Support Batch in cuda
Support f32 to f32 both in cpu && cuda
3. DepthWiseConv:
Support by Im2Col && MulMat
4. Pool_2d:
Supoort avg pooling in cuda
5. HardSigmoid:
Imp in cuda
6. HardSwish:
Imp in cuda
* fix tabs instead of spaces
* code clean
* CUDA POOL2D
* ADD POOL2D test case in test-backend-ops.cpp
* code clean
* fix pool2d_kernel
nits
* fix bug in pool2d kernel
* fix avg pooling, count_include_pad
nits
* test-backend-ops : add more pool_2d tests
* cuda : fix warnings and formatting
* ggml : check types in release builds too in pool_2d
* test-backend-ops : remove f16 pool_2d tests
* cuda : more style fixes
* Add assert in ggml_cuda_op_pool2d
* pool2d float padding fallback
* test-backend-ops : add dst_type to im2col
---------
Co-authored-by: slaren <slarengh@gmail.com>
Diffstat (limited to 'common/common.cpp')
0 files changed, 0 insertions, 0 deletions