| .. |
|
alibi.h
|
Change inline to __forceinline__, use __grid_constant__ param
|
2024-01-20 17:38:47 -08:00 |
|
block_info.h
|
Change inline to __forceinline__, use __grid_constant__ param
|
2024-01-20 17:38:47 -08:00 |
|
dropout.h
|
Refactor masking in fwd pass into 1 object
|
2024-01-20 17:39:53 -08:00 |
|
flash_bwd_hdim32_bf16_sm80.cu
|
Remove configure in bwd kernel launch
|
2024-01-21 15:28:33 -08:00 |
|
flash_bwd_hdim32_fp16_sm80.cu
|
Remove configure in bwd kernel launch
|
2024-01-21 15:28:33 -08:00 |
|
flash_bwd_hdim64_bf16_sm80.cu
|
Remove configure in bwd kernel launch
|
2024-01-21 15:28:33 -08:00 |
|
flash_bwd_hdim64_fp16_sm80.cu
|
Remove configure in bwd kernel launch
|
2024-01-21 15:28:33 -08:00 |
|
flash_bwd_hdim96_bf16_sm80.cu
|
Remove configure in bwd kernel launch
|
2024-01-21 15:28:33 -08:00 |
|
flash_bwd_hdim96_fp16_sm80.cu
|
Remove configure in bwd kernel launch
|
2024-01-21 15:28:33 -08:00 |
|
flash_bwd_hdim128_bf16_sm80.cu
|
Remove configure in bwd kernel launch
|
2024-01-21 15:28:33 -08:00 |
|
flash_bwd_hdim128_fp16_sm80.cu
|
Remove configure in bwd kernel launch
|
2024-01-21 15:28:33 -08:00 |
|
flash_bwd_hdim160_bf16_sm80.cu
|
Remove configure in bwd kernel launch
|
2024-01-21 15:28:33 -08:00 |
|
flash_bwd_hdim160_fp16_sm80.cu
|
Remove configure in bwd kernel launch
|
2024-01-21 15:28:33 -08:00 |
|
flash_bwd_hdim192_bf16_sm80.cu
|
Remove configure in bwd kernel launch
|
2024-01-21 15:28:33 -08:00 |
|
flash_bwd_hdim192_fp16_sm80.cu
|
Remove configure in bwd kernel launch
|
2024-01-21 15:28:33 -08:00 |
|
flash_bwd_hdim224_bf16_sm80.cu
|
Remove configure in bwd kernel launch
|
2024-01-21 15:28:33 -08:00 |
|
flash_bwd_hdim224_fp16_sm80.cu
|
Remove configure in bwd kernel launch
|
2024-01-21 15:28:33 -08:00 |
|
flash_bwd_hdim256_bf16_sm80.cu
|
Remove configure in bwd kernel launch
|
2024-01-21 15:28:33 -08:00 |
|
flash_bwd_hdim256_fp16_sm80.cu
|
Remove configure in bwd kernel launch
|
2024-01-21 15:28:33 -08:00 |
|
flash_bwd_kernel.h
|
Enable headdim 256 backward on consumer GPUs (Ampere, Ada)
|
2024-02-21 15:56:19 -08:00 |
|
flash_bwd_launch_template.h
|
Add in, macrosf for defining __grid_constant__ (#852)
|
2024-03-15 00:48:54 -07:00 |
|
flash_bwd_preprocess_kernel.h
|
Move bwd preprocess kernels to a separate file
|
2024-01-14 16:57:03 -08:00 |
|
flash_fwd_hdim32_bf16_sm80.cu
|
Use generate_kernels.py script from Driss Guessous
|
2023-08-28 13:34:12 -07:00 |
|
flash_fwd_hdim32_fp16_sm80.cu
|
Use generate_kernels.py script from Driss Guessous
|
2023-08-28 13:34:12 -07:00 |
|
flash_fwd_hdim64_bf16_sm80.cu
|
Use generate_kernels.py script from Driss Guessous
|
2023-08-28 13:34:12 -07:00 |
|
flash_fwd_hdim64_fp16_sm80.cu
|
Use generate_kernels.py script from Driss Guessous
|
2023-08-28 13:34:12 -07:00 |
|
flash_fwd_hdim96_bf16_sm80.cu
|
Use generate_kernels.py script from Driss Guessous
|
2023-08-28 13:34:12 -07:00 |
|
flash_fwd_hdim96_fp16_sm80.cu
|
Use generate_kernels.py script from Driss Guessous
|
2023-08-28 13:34:12 -07:00 |
|
flash_fwd_hdim128_bf16_sm80.cu
|
Use generate_kernels.py script from Driss Guessous
|
2023-08-28 13:34:12 -07:00 |
|
flash_fwd_hdim128_fp16_sm80.cu
|
Use generate_kernels.py script from Driss Guessous
|
2023-08-28 13:34:12 -07:00 |
|
flash_fwd_hdim160_bf16_sm80.cu
|
Use generate_kernels.py script from Driss Guessous
|
2023-08-28 13:34:12 -07:00 |
|
flash_fwd_hdim160_fp16_sm80.cu
|
Use generate_kernels.py script from Driss Guessous
|
2023-08-28 13:34:12 -07:00 |
|
flash_fwd_hdim192_bf16_sm80.cu
|
Use generate_kernels.py script from Driss Guessous
|
2023-08-28 13:34:12 -07:00 |
|
flash_fwd_hdim192_fp16_sm80.cu
|
Use generate_kernels.py script from Driss Guessous
|
2023-08-28 13:34:12 -07:00 |
|
flash_fwd_hdim224_bf16_sm80.cu
|
Use generate_kernels.py script from Driss Guessous
|
2023-08-28 13:34:12 -07:00 |
|
flash_fwd_hdim224_fp16_sm80.cu
|
Use generate_kernels.py script from Driss Guessous
|
2023-08-28 13:34:12 -07:00 |
|
flash_fwd_hdim256_bf16_sm80.cu
|
Use generate_kernels.py script from Driss Guessous
|
2023-08-28 13:34:12 -07:00 |
|
flash_fwd_hdim256_fp16_sm80.cu
|
Use generate_kernels.py script from Driss Guessous
|
2023-08-28 13:34:12 -07:00 |
|
flash_fwd_kernel.h
|
Minor fix in compute_attn_1rowblock_splitkv (#900)
|
2024-03-27 19:11:45 -07:00 |
|
flash_fwd_launch_template.h
|
Add in, macrosf for defining __grid_constant__ (#852)
|
2024-03-15 00:48:54 -07:00 |
|
flash_fwd_split_hdim32_bf16_sm80.cu
|
Implement splitKV attention
|
2023-08-29 00:58:29 -07:00 |
|
flash_fwd_split_hdim32_fp16_sm80.cu
|
Implement splitKV attention
|
2023-08-29 00:58:29 -07:00 |
|
flash_fwd_split_hdim64_bf16_sm80.cu
|
Implement splitKV attention
|
2023-08-29 00:58:29 -07:00 |
|
flash_fwd_split_hdim64_fp16_sm80.cu
|
Implement splitKV attention
|
2023-08-29 00:58:29 -07:00 |
|
flash_fwd_split_hdim96_bf16_sm80.cu
|
Implement splitKV attention
|
2023-08-29 00:58:29 -07:00 |
|
flash_fwd_split_hdim96_fp16_sm80.cu
|
Implement splitKV attention
|
2023-08-29 00:58:29 -07:00 |
|
flash_fwd_split_hdim128_bf16_sm80.cu
|
Implement splitKV attention
|
2023-08-29 00:58:29 -07:00 |
|
flash_fwd_split_hdim128_fp16_sm80.cu
|
Implement splitKV attention
|
2023-08-29 00:58:29 -07:00 |
|
flash_fwd_split_hdim160_bf16_sm80.cu
|
Implement splitKV attention
|
2023-08-29 00:58:29 -07:00 |
|
flash_fwd_split_hdim160_fp16_sm80.cu
|
Implement splitKV attention
|
2023-08-29 00:58:29 -07:00 |
|
flash_fwd_split_hdim192_bf16_sm80.cu
|
Implement splitKV attention
|
2023-08-29 00:58:29 -07:00 |
|
flash_fwd_split_hdim192_fp16_sm80.cu
|
Implement splitKV attention
|
2023-08-29 00:58:29 -07:00 |
|
flash_fwd_split_hdim224_bf16_sm80.cu
|
Implement splitKV attention
|
2023-08-29 00:58:29 -07:00 |
|
flash_fwd_split_hdim224_fp16_sm80.cu
|
Implement splitKV attention
|
2023-08-29 00:58:29 -07:00 |
|
flash_fwd_split_hdim256_bf16_sm80.cu
|
Implement splitKV attention
|
2023-08-29 00:58:29 -07:00 |
|
flash_fwd_split_hdim256_fp16_sm80.cu
|
Implement splitKV attention
|
2023-08-29 00:58:29 -07:00 |
|
flash.h
|
Implement page KV cache
|
2024-01-22 22:47:30 -08:00 |
|
generate_kernels.py
|
Remove configure in bwd kernel launch
|
2024-01-21 15:28:33 -08:00 |
|
kernel_traits.h
|
Enable headdim 256 backward on consumer GPUs (Ampere, Ada)
|
2024-02-21 15:56:19 -08:00 |
|
mask.h
|
Refactor masking in fwd pass into 1 object
|
2024-01-20 17:39:53 -08:00 |
|
philox.cuh
|
Change inline to __forceinline__, use __grid_constant__ param
|
2024-01-20 17:38:47 -08:00 |
|
rotary.h
|
Move rotary device functions to a separate file
|
2024-01-20 18:01:18 -08:00 |
|
softmax.h
|
Add the option for the macro and note (#893)
|
2024-03-27 19:12:11 -07:00 |
|
static_switch.h
|
Preprocessor switches to control functionality (#788)
|
2024-01-29 20:44:23 -08:00 |
|
utils.h
|
Move rotary device functions to a separate file
|
2024-01-20 18:01:18 -08:00 |
