Delay materializing the replaced model weights until quantization #1307
refine replacement logic
e337b226
refine gpt-oss
48f12731
enhance memory monitor
7e5a9d7b
fix
23334a00
update replace logic
d87613bb
fix
0111ae43
clean
3379e6ff
fix
21ca1e48
refine name
2e8b438b
refactor ds
2ba764c6
fix
bfe8f884
refactor llama4
8e0c98f5
add note
56119be7
revert test change
f8bc90b2
yiliu30
marked this pull request as ready for review 250 days ago
merge main
b3610d71
[pre-commit.ci] auto fixes from pre-commit.com hooks
43db8151
add utils
37ccbeae
Merge branch 'lazy-replace' of https://github.com/intel/auto-round in…
cefb707f
fix
e2ae147e
Merge branch 'main' into lazy-replace
4efcd4d9
fix
eac43657
Merge branch 'lazy-replace' of https://github.com/intel/auto-round in…
c64ede0e
fix cpu ut
48a9c600
add safe to cpu
69a9e207
tmp debug
299f3026
Merge branch 'main' into lazy-replace
7f00ed49
fix llama
3e0e8c08
Merge branch 'lazy-replace' of https://github.com/intel/auto-round in…
efd931dc
quick fix
ba559bf1
Merge branch 'main' into lazy-replace
57313011
fix
d2c59960
Merge branch 'lazy-replace' of https://github.com/intel/auto-round in…
bafa5f63
update
0ae01b5c
merge main
8e026922
fix
a41b69ab
fix
2ad016ad
fix
bfde825b
clean code
ab22a915
clean code
41ade145
update
b98982c0
fix
4c9e59ee
add more mem logger
23661c03
fix format
aa129668
revert clean module name
f6d39cf3
refactor models
00279431
format
18043c58
fix ds
9d00eb7b
clean
c7bec548
clean
ae893c54
update note
f4e5c7f6
Merge branch 'main' into lazy-replace
87677d09
Merge branch 'lazy-replace' of https://github.com/intel/auto-round in…
20ce9fb9
global state
5b4a2c92
[pre-commit.ci] auto fixes from pre-commit.com hooks
5b97021c
fix imatrix
c7181ebb
Merge branch 'main' into lazy-replace
c0860152
fix
59b9ab92
update
81cb1525
Merge branch 'main' into lazy-replace
f9f139df
add safe to cpu
ab05f4d9
fix ut
e80fe994
yiliu30
merged
d9d20a12
into main 245 days ago
yiliu30
deleted the lazy-replace branch 245 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub