57 lines
2.5 KiB
Plaintext
57 lines
2.5 KiB
Plaintext
tree 3d665a651996d86e564ea6fa9c990c05e7f593c6
|
|
parent d4fbdb01390230d02d4b33c9b4ad721321f22d67
|
|
author rattus <46076784+rattus128@users.noreply.github.com> 1762554680 +1000
|
|
committer GitHub <noreply@github.com> 1762554680 +0100
|
|
gpgsig -----BEGIN PGP SIGNATURE-----
|
|
|
|
wsFcBAABCAAQBQJpDnM4CRC1aQ7uu5UhlAAAIQQQAGhLPK3SczyixyuOxRyctMJ3
|
|
4JvHw8spOTJool0QzY4PvyrLSrITz5Vz0ctrKMVOy2xvJJTDrCg9t90jFTDTUPuN
|
|
9SHK23TcwExr62mSbMdcL5WnhpUyI3PKDO/6yM3Fxxtx/f6gxxkndrYly6Hj6JEV
|
|
og5zY8lIItV+pNQ4Flm+rTlEGdxRunfXJ2fjHR5//TWRnJvZTCrW0JsLh+QkBaCs
|
|
prqXxJK4EGibFENhPk+peXoHnQMMlrTTRF7IqWauJ2mCZA1+l92msjTAPFrUwPdl
|
|
I14ws8wUerxSDQX+S6OJe40Stu7gfkZ1Gr2gCwpUXzX+7jJK7qgsDqDeu8MfblQS
|
|
AoRoS8p+SSeSPufQRlICx3NkAczy+IrfUOeV8itfSFGw0Bh6R+HLYaJPjqfE1xgy
|
|
yLpbZ0TplkR8gjfVyD/NBNzKkvHdoMB8Pp7MhpwtWkdYBUX5pRObw9FqxXKPR0BJ
|
|
hG+hWuATafSuKzhuoADObvmRLqajAbHbp3AhP/NdJ4p+mTQ6s6mZn1BYEjRWyI5Y
|
|
DgXPr7tZzxkcIMpEFTy9oX24av9Z7OKGwFUTmUaG5NRYXqqUEf/tFU3qKKMnpMmm
|
|
7qMqfySspSwIUlxn5o2K/eZ0ybueokU7XysQrnv1TjUA8XosHEk28N0/jPlRvnnr
|
|
8EfgFlbwjr/RsXOvMThg
|
|
=ai1V
|
|
-----END PGP SIGNATURE-----
|
|
|
|
|
|
add default named_modules_to_munmap variable (#357)
|
|
|
|
* add default named_modules_to_munmap variable
|
|
|
|
Default this to handle to case of cloning a GGUFModelPatcher which then
|
|
expects it to exist on the clone.
|
|
|
|
I could never reproduce this condition, however 4 users have the error.
|
|
This error path is very sensitive to VRAM condtions and workflow and I
|
|
never got the details so its a bit of a guess.
|
|
|
|
But from a code point of view, its the right thing anyway
|
|
|
|
* nodes: carry the mmap_released state through a clone()
|
|
|
|
There are workflows where the same underlying model will be loaded
|
|
twice by two different ModelPatchers.
|
|
|
|
With the current code as-is, the first patcher will load fine and
|
|
intercept the pins while removing already done pins from the free
|
|
modules list.
|
|
|
|
It then will load again with the second MP however, this one will
|
|
not get the callbacks for the already pinned stuff and then rip
|
|
through and .to().to() them all. This destroys the pinning setup
|
|
while comfy core still keeps the modules registered as unpinned.
|
|
This causes a crash on einval when core goes to unpin the not pinned
|
|
tensors.
|
|
|
|
Comfy core now has a guard against unpinning the not-pinned, however
|
|
what I think is happening, is the RAM of the pin in freed in the
|
|
.to().to() and then malloc re-allocates it to new tensors with cuda
|
|
keeping its records of previous pinning. einval can happen when
|
|
you try and unpin a tensor in the middle of the block which is
|
|
definately possible on this use after free pattern. |