 Tri Dao
|
844912dca0
[CI] Switch from CUDA 12.2 to 12.3
|
il y a 5 mois |
|
Tri Dao
|
116b05f9b0
[CI] Compile with pytorch 2.4.0.dev20240514
|
il y a 5 mois |
|
Tri Dao
|
beb2bf2a32
Drop support for pytorch 1.12, 1.13, and python 3.7
|
il y a 5 mois |
|
Tri Dao
|
e2e4333c95
Limit to MAX_JOBS=1 with CUDA 12.2
|
il y a 6 mois |
|
Tri Dao
|
af627063e3
[CI] Compile for pytorch 2.4.0.dev20240407 (for nvcr 24.05)
|
il y a 6 mois |
 Wongboo
|
40e667236c
Update for python3.12 (#870)
|
il y a 6 mois |
|
Tri Dao
|
35060e7450
[CI] Compile for pytorch 2.2.2 and 2.3.0
|
il y a 7 mois |
|
Tri Dao
|
2aea958f89
[CI] Compile with torch 2.3.0.dev20240207
|
il y a 8 mois |
|
Tri Dao
|
6e2fa30797
[CI] Change torch 2.3.0.dev20240126 to 20240105 for nvcr 24.02
|
il y a 9 mois |
|
Tri Dao
|
6a5c053c3e
[CI] Compile with torch 2.2.0 instead of 2.2.0.dev20231106
|
il y a 10 mois |
|
Tri Dao
|
dc72d960a7
[CI] Install torch 2.3 using index
|
il y a 10 mois |
|
Tri Dao
|
aa2eb8ddf2
[CI] Compile with pytorch 2.2.0.dev20231106
|
il y a 10 mois |
 Christian Kadner
|
290596c544
[CI] Build wheels for Pytorch 2.3 (dev/nightly) (#793)
|
il y a 10 mois |
|
Tri Dao
|
e43a4ceaab
[CI] Fix CUDA 12.2.2 compilation
|
il y a 10 mois |
|
Tri Dao
|
0399432d68
[CI] Use CUDA 12.2.2 instead of 12.2.0
|
il y a 10 mois |
|
Tri Dao
|
43ceab630b
[CI] Use torch nightly 20231130 instead of 20231106
|
il y a 11 mois |
|
Tri Dao
|
68f178aa4b
[CI] Don't compile for python 3.7 pytorch 2.2
|
il y a 11 mois |
|
Tri Dao
|
701b51bfc3
[CI] Use torch-nightly 20231106 instead of 20231127
|
il y a 1 an |
|
Tri Dao
|
d4a7c8ffbb
[CI] Only compile for CUDA 11.8 & 12.2, MAX_JOBS=2,add torch-nightly
|
il y a 1 an |
|
Tri Dao
|
5e525a8dc8
[CI] Use official Pytorch 2.1, add CUDA 11.8 for Pytorch 2.1
|
il y a 1 an |
|
Tri Dao
|
799f56fa90
Don't compile for Pytorch 2.1 on CUDA 12.1 due to nvcc segfaults
|
il y a 1 an |
|
Tri Dao
|
4976650f74
Set single threaded compilation for CUDA 12.2 so CI doesn't OOM
|
il y a 1 an |
|
Tri Dao
|
1dc1b6c8f2
Bump to v2.1.2
|
il y a 1 an |
|
Tri Dao
|
08e9847176
[CI] Add CUDA 12.2
|
il y a 1 an |
|
Tri Dao
|
2286d7cea7
Bump to v2.0.8
|
il y a 1 an |
|
Tri Dao
|
c65b5106ac
Fix Bwd NaN for varlen when seqlen_q >> seqlen_k and causal
|
il y a 1 an |
|
Tri Dao
|
f8dccfc90a
[CI] Fix MATRIX_CUDA_VERSION check
|
il y a 1 an |
|
Tri Dao
|
9c531bdc0a
Use single thread compilation for cuda12.1, torch2.1 to avoid OOM CI
|
il y a 1 an |
|
Tri Dao
|
2ddeaa406c
Fix wheel building
|
il y a 1 an |
 Pierce Freeman
|
6ef3bd800e
Install standard non-wheel package
|
il y a 1 an |
