Tri Dao
6a77a6da10
Refactor gemm_cl to template on either __half or __nv_bfloat16
2022-07-09 23:18:26 -07:00
Tri Dao
e518a4b327
Refactor to template on __half, implement bf16 util functions
2022-07-09 23:18:26 -07:00
Tri Dao
2dc1b205f6
Fix Illegal Memory Access bug in fwd when d=16
2022-07-09 23:17:14 -07:00
Tri Dao
5b838a8bef
Apply dropout scaling to dQ and dK instead of to V (in bwd)
...
Theoretically this might have lower numerical error since the scaling is in
fp32 instead of fp16 (not sure, I haven't thought too carefully about it).
However, in practice, the numerical errors seem about the same.
2022-07-03 17:53:37 -07:00
Tri Dao
a5559a0e75
Do P * dP (pointwise) in the bwd in fp32 instead of fp16
2022-07-03 17:52:05 -07:00
Tri Dao
6c3a8c65af
Implement cross attention
2022-07-03 17:48:12 -07:00
Tri Dao
f66603cb6f
Support batch size > 64K by swapping grid.x and grid.y
2022-06-29 23:16:24 -07:00
Tri Dao
c0daa62eaa
Add type check (fp16) in the forward pass
2022-06-26 11:41:30 -07:00
Tri Dao
ea38d3d261
Fix race condition in backward pass (smem_dq)
2022-06-25 18:02:30 -07:00
Tri Dao
eeca63a72a
Bug fix: wrong smem_o write pointer for d=16
2022-06-25 15:18:33 -07:00
Tri Dao
5d07483bbc
Refactor Gmem code to store q, k, v pointers separately
2022-06-12 16:37:32 -07:00
Tri Dao
d3e6440958
Implement bwd for head dim 128
2022-06-11 17:52:36 -07:00
Tri Dao
0d854692c6
Implement fwd for head dim 128
2022-06-11 17:52:36 -07:00
Tri Dao
321c57d07d
Set block size of SM75 fwd to 256 if there's no dropout
...
This speeds up the fwd by 1.5x.
2022-06-04 16:51:28 -07:00
Tri Dao
d380e87fb6
Don't use Smem_dp_sum in backward pass
...
To reduce smem usage for SM75
2022-06-04 16:01:36 -07:00
Tri Dao
b17c6fe235
Reduce smem usage for Q and dO in the backward pass
...
From 4KB per buffer to 2KB per buffer. This saves us 8KB of smem (each Q and dO
have 2 buffers)
2022-06-03 16:59:11 -07:00
Tri Dao
2712aa4c8d
Support Turing mma instructions
2022-06-03 16:58:44 -07:00
Tri Dao
050873327e
Remove softmax fp16 max
2022-06-02 14:09:46 -07:00
Tri Dao
14dc326e59
Use Cutlass gemm as WarpMma
2022-06-02 10:33:32 -07:00
Tri Dao
e78e7c9553
Remove old backward
2022-06-02 10:13:44 -07:00
Tri Dao
512c98ee05
Add Cutlass as submodule
2022-06-02 09:54:16 -07:00
Tri Dao
5a61cb7729
Rename src -> flash_attn
2022-06-01 18:50:26 -07:00
Tri Dao
c41479d66d
Support SM86 GPUs
2022-06-01 18:49:47 -07:00
Tri Dao
9dbc491aa5
Rename, add benchmarking script
2022-05-26 13:57:38 -07:00
