| .. |
|
cuda_attention_kvcache.h
|
[feature] add fused attention_kvcache operator support (#179)
|
2023-11-14 23:44:22 +08:00 |
|
cuda_clip.h
|
Dev for 202303ddl (#66)
|
2023-04-18 15:10:33 +08:00 |
|
cuda_common.h
|
tensor parallel for transformer (#125)
|
2023-09-14 14:19:45 +08:00 |
|
cuda_element_wise.h
|
support Dynamic tensor infer shape and fix memory pool (#176)
|
2023-11-23 13:11:50 +08:00 |
|
cuda_expand.h
|
"modified where" (#131)
|
2023-09-14 10:45:57 +08:00 |
|
cuda_kernel_wihtout_config.h
|
ADD: batch norm operator and cuda kernel. (#44)
|
2022-10-15 16:29:28 +08:00 |
|
cuda_layernorm.h
|
Add layer normalization (#181)
|
2023-11-24 15:15:14 +08:00 |
|
cuda_pad_slice.h
|
support Dynamic tensor infer shape and fix memory pool (#176)
|
2023-11-23 13:11:50 +08:00 |
|
cuda_runtime.h
|
impl distributed launch with NCCL (#106)
|
2023-09-05 09:47:35 +08:00 |
|
cuda_softmax.h
|
modified all register kernel
|
2023-12-07 17:53:28 +08:00 |
|
cuda_split_concat.h
|
support 8D tensor, add test example (#170)
|
2023-10-31 10:47:36 +08:00 |
|
cuda_transpose.h
|
Add cuda transpose kernel (#115)
|
2023-08-22 14:22:15 +08:00 |
|
cuda_unary.h
|
Add HardSigmoid and HardSwish (#156)
|
2023-10-10 22:41:06 +08:00 |
|
cuda_utility.h
|
- Remove dataType from the kernel registration.
|
2023-11-30 13:51:24 +08:00 |
|
cuda_where.h
|
add where fp16
|
2023-12-08 16:57:49 +08:00 |
|
gather.h
|
Add GatherElements op and cuda kernel (#149)
|
2023-10-12 09:18:12 +08:00 |
|
gbmm_g2bmm.cuh
|
Fix CMake USE_CUDA (#36)
|
2022-09-21 12:28:00 +08:00 |
|
gbmm_g2bmm.h
|
Fix CMake USE_CUDA (#36)
|
2022-09-21 12:28:00 +08:00 |
|
nccl_communicator.h
|
impl distributed launch with NCCL (#106)
|
2023-09-05 09:47:35 +08:00 |
|
operator_timer.h
|
ADD: batch norm operator and cuda kernel. (#44)
|
2022-10-15 16:29:28 +08:00 |
|
resize.cuh
|
ADD: reconfig ResizeObj, support "tf_crop_and_resize " and cubic coeff kernel. (#59)
|
2022-12-24 04:02:21 +08:00 |
8b2e3b8e19