Commit Graph

159 Commits

Author SHA1 Message Date
Nicolas Patry 662e073668
priv-cache. 2024-09-17 17:26:37 +02:00
Nicolas Patry 2d3afb3274
Wtf state. 2024-09-17 16:31:06 +02:00
Nicolas Patry 911f82a34b
Using the cache on both jobs. 2024-09-17 14:05:06 +02:00
Nicolas Patry df4b1ec936
Remove NCCL debug. 2024-09-17 11:13:11 +02:00
Nicolas Patry 666d946ed7
Give me the rights. 2024-09-17 10:43:45 +02:00
Nicolas Patry bec5c94714
No capsys inside docker. 2024-09-17 10:35:18 +02:00
Nicolas Patry 06cee05d44
O bind what ? 2024-09-17 10:34:32 +02:00
Nicolas Patry 1333c58b62
Syntax ? 2024-09-17 10:33:23 +02:00
Nicolas Patry 123a59531d
Attempt a bind instead of symlink. 2024-09-17 10:30:14 +02:00
Nicolas Patry c584443373
Symlink doesn't work 2024-09-17 10:27:08 +02:00
Nicolas Patry dc2e1a36e0
Fix ? 2024-09-17 10:23:01 +02:00
Nicolas Patry b74f335b02
Give access to runner. 2024-09-17 10:21:32 +02:00
Nicolas Patry 54e703cc5a
Create /nix before the action creates it. 2024-09-17 10:19:22 +02:00
Nicolas Patry 1ff5b64b1c
OMG. 2024-09-17 10:16:26 +02:00
Nicolas Patry e680a57147
Disabling the sharding please. 2024-09-17 10:12:52 +02:00
Nicolas Patry 5827137a29
Wtf ? 2024-09-17 10:04:43 +02:00
Nicolas Patry c859663f98
NCCL attempts 2024-09-17 09:43:28 +02:00
Nicolas Patry 7a5855ff01
NCCL ? 2024-09-17 09:37:05 +02:00
Nicolas Patry fb7e8c8970
Add the cache. 2024-09-17 09:20:12 +02:00
Guillaume LEGENDRE 2aa2851e01
use runners with cache 2024-09-17 08:12:19 +02:00
Nicolas Patry 87c85fdc38
Standard setup. 2024-09-16 17:04:11 +02:00
Nicolas Patry 69c20a9d3f
Tmate let's find with ldconfig ? 2024-09-16 17:03:28 +02:00
Nicolas Patry c784cb401d
Let's try a compat drvier ? 2024-09-16 17:03:28 +02:00
Nicolas Patry fe533dc57b
Back to failing version 2024-09-16 17:03:28 +02:00
Nicolas Patry 2f1f082abe
Tmate. 2024-09-16 17:03:28 +02:00
Nicolas Patry 1a6b9926f6
missing lib. 2024-09-16 17:03:27 +02:00
Nicolas Patry 332e42f59a
Attempt. 2024-09-16 17:03:27 +02:00
Nicolas Patry ec6fe324c6
Link to nix owned lib 2024-09-16 17:03:27 +02:00
Nicolas Patry 83ee55a617
Trye somethign. 2024-09-16 17:03:27 +02:00
Nicolas Patry 047530216c
No idea where the shared disk is. 2024-09-16 17:03:27 +02:00
Nicolas Patry 9f548fa82a
Change the home location ? 2024-09-16 17:03:27 +02:00
Nicolas Patry 3ff12084b7
Revert "No tmate."
This reverts commit 6b9b6d951897127ae1ce09c8f61f86a64b301fec.
2024-09-16 17:03:26 +02:00
Nicolas Patry 26634f9697
No tmate. 2024-09-16 17:03:26 +02:00
Nicolas Patry a533d086f0
Tmate to find cache. 2024-09-16 17:03:26 +02:00
Nicolas Patry a5b81ab457
Home. 2024-09-16 17:03:26 +02:00
Nicolas Patry 98f2241a88
Put back libnvidia-ml 2024-09-16 17:03:26 +02:00
Nicolas Patry 72a805d50d
Remove tmate. 2024-09-16 17:03:26 +02:00
Nicolas Patry 45c0129976
Attempting something. 2024-09-16 17:03:25 +02:00
Nicolas Patry 2b18537f85
More tmate. 2024-09-16 17:03:25 +02:00
Nicolas Patry 12b88204b0
Putting the cuda package in the flake. 2024-09-16 17:03:25 +02:00
Nicolas Patry d7333830b5
Tmate. 2024-09-16 17:03:25 +02:00
Nicolas Patry c4bbe06bf1
Simpler command 2024-09-16 17:02:45 +02:00
Nicolas Patry d0ae24a167
Release tests. 2024-09-16 17:02:25 +02:00
Nicolas Patry 5c4b2eaa30
Seeing the damage on the release tests. 2024-09-16 17:01:51 +02:00
Nicolas Patry 70f910bba6
Remove tmate. 2024-09-16 17:01:51 +02:00
Nicolas Patry 5adece6313
This doesn't seem needed. 2024-09-16 17:01:51 +02:00
Nicolas Patry b7cb8d5145
Let's figure out the issue... 2024-09-16 17:01:30 +02:00
Nicolas Patry 3d7b81535a
Only link cuda driver librairies. 2024-09-16 17:01:30 +02:00
Nicolas Patry ce3efc83ed
Remove tmate. 2024-09-16 17:01:30 +02:00
Nicolas Patry 7f58f7dc61
Symlink all the things. 2024-09-16 17:01:29 +02:00