Stella Laurenzo
commited on
Commit
·
d30d6ff
1
Parent(s):
1fc8739
Update unet assets for fused qkv quantization.
Browse filesThis is based off of code changes: https://github.com/nod-ai/sharktank/pull/106
unet/int8/export/sdxl_unet_int8_dataset.irpa
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ce953fbe4a576f7ca31f6816651645d4d36055864273a1d49de3a552b197a42
|
3 |
+
size 2616446976
|
unet/int8/export/sdxl_unet_int8_export.mlir
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9658d9696af26189a8fa769354a94b6c4b98c1ce167436273874db402b44e92
|
3 |
+
size 7531047
|
unet/int8/params.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56402309091a6180f85ee4c1a454f272030182a8a0d583e92c7945de6dbc6604
|
3 |
+
size 5136147144
|
unet/int8/quant_params.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35a2ad3fff64594a6d512105d61529864e27827035f7bd728f15d1b63cc64eff
|
3 |
+
size 80112598
|