1.8X speedup by disable_low_gpu_mem_usage and reduce memory usage by avoid using torch.cat #106
fix a bug in example
7d020db2
Merge branch 'main' of https://github.com/intel/auto-round
fbe69d5c
Merge branch 'main' of https://github.com/intel/auto-round
596a18f5
Merge branch 'main' of https://github.com/intel/auto-round
10add8ce
Merge branch 'main' of https://github.com/intel/auto-round
003b60a6
Merge branch 'main' of https://github.com/intel/auto-round
9d495140
Merge branch 'main' of https://github.com/intel/auto-round
3b7f386c
Merge branch 'main' of https://github.com/intel/auto-round
d3f14df6
Merge branch 'main' of https://github.com/intel/auto-round
76e4d909
Merge branch 'main' of https://github.com/intel/auto-round
08e46acb
Merge branch 'main' of https://github.com/intel/auto-round
15b756b0
Merge branch 'main' of https://github.com/intel/auto-round
40425bbd
Merge branch 'main' of https://github.com/intel/auto-round
f0b9ad00
Merge branch 'main' of https://github.com/intel/auto-round
04e70eca
Merge branch 'main' of https://github.com/intel/auto-round
43811bb9
Merge branch 'main' of https://github.com/intel/auto-round
c8817199
Merge branch 'main' of https://github.com/intel/auto-round
54920e56
Merge branch 'main' of https://github.com/intel/auto-round
e2c2f56c
Merge branch 'main' of https://github.com/intel/auto-round
4f718d45
Merge branch 'main' of https://github.com/intel/auto-round
022988aa
fix performance regression
446f52f8
not using torch cat to avoid torch tricky gpu memory issue
d1c00771
[pre-commit.ci] auto fixes from pre-commit.com hooks
21508d33
fix one issue
52df5141
Merge branch 'fix_performance' of https://github.com/intel/auto-round…
9ff10837
remove the torch.cuda.empty_cache in each iters, which improve the sp…
030c9264
[pre-commit.ci] auto fixes from pre-commit.com hooks
7a23be47
wenhuach21
changed the title 2X speedup with disable_low_gpu_mem by fix performance regression 2X+ speedup by fix performance regression and avoid using torch.cat to reduce weird and large memory footprint 2 years ago
fix some issue
945f3e6e
torch.no_grad -> torch.inference_mode
2d935d43
torch.no_grad -> torch.inference_mode
83261bdf
[pre-commit.ci] auto fixes from pre-commit.com hooks
205435d1
tiny change
512263ce
polish code and fix some issues
72305a83
Merge branch 'fix_performance' of https://github.com/intel/auto-round…
9952271a
[pre-commit.ci] auto fixes from pre-commit.com hooks
06026ca2
wenhuach21
changed the title 2X+ speedup by fix performance regression and avoid using torch.cat to reduce weird and large memory footprint speedup by disable_low_gpu_mem_usage and reduce memory usage by avoid using torch.cat 2 years ago
add trust_remote_code
a0236393
Merge branch 'fix_performance' of https://github.com/intel/auto-round…
b77c3aeb
fix chatglm3 bug
905085b8
[pre-commit.ci] auto fixes from pre-commit.com hooks
a905d9a6
revert inference mode to no_grad as some issue occurs in phi2
595316f7
[pre-commit.ci] auto fixes from pre-commit.com hooks
2bdd602d
fix a critical regression
ef52934c
fix conv1d issue
13a82208
add comments
c202979f
[pre-commit.ci] auto fixes from pre-commit.com hooks
b102fe78
update readme
db29840d
wenhuach21
changed the title speedup by disable_low_gpu_mem_usage and reduce memory usage by avoid using torch.cat ~80% speedup by disable_low_gpu_mem_usage and reduce memory usage by avoid using torch.cat 2 years ago
wenhuach21
changed the title ~80% speedup by disable_low_gpu_mem_usage and reduce memory usage by avoid using torch.cat 1.8X speedup by disable_low_gpu_mem_usage and reduce memory usage by avoid using torch.cat 2 years ago
fix typo
61d2b351
wenhuach21
deleted the fix_performance branch 2 years ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub