Skip to content

[Inductor][float8] Support qlinear for float8 in inductor #2565

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 33 commits into
base: main
Choose a base branch
from
Open

[Inductor][float8] Support qlinear for float8 in inductor #2565

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
33 commits
Select commit Hold shift + click to select a range
a840ef5
quantize_affine_float8/dequantize_affine_float8 not decomposed on ind…
shiyang-weng Jun 16, 2025
02d045b
remove redundant unittest.skipIf
shiyang-weng Jun 16, 2025
9860c56
fix rebase issue
shiyang-weng Jun 18, 2025
ca662f3
change dispatch key to a flag decomposed
shiyang-weng Jun 18, 2025
f51a5be
support scaled_mm on inductor
shiyang-weng Jun 18, 2025
719793c
fix rebase issue
shiyang-weng Jun 18, 2025
48a3d99
support dequant promtion for fp8
shiyang-weng Jun 25, 2025
1921b2f
add ut
shiyang-weng Jun 25, 2025
0335415
remove redundant codes
shiyang-weng Jun 25, 2025
955fa6e
Merge pull request #2 from shiyang-weng/wengshiy/dequant_promotion
shiyang-weng Jun 25, 2025
a70e094
Merge remote-tracking branch 'origin/main' into wengshiy/scaled_mm
shiyang-weng Jun 25, 2025
a5bb4d0
fix lint
shiyang-weng Jun 25, 2025
1c1f890
Merge branch 'main' into wengshiy/scaled_mm
shiyang-weng Jun 25, 2025
0c7f8ea
resolve conflict
shiyang-weng Jun 25, 2025
0175b17
change to use qlinear
shiyang-weng Jul 1, 2025
564d4b7
add ut
shiyang-weng Jul 7, 2025
9948674
fix lint
shiyang-weng Jul 7, 2025
413a883
Merge remote-tracking branch 'origin/main' into wengshiy/qlinear
shiyang-weng Jul 7, 2025
558d216
support fp8 quant_lift_up
shiyang-weng Jul 11, 2025
8cd1433
add reshape into _VIEW_METHOD_OPS
shiyang-weng Jul 15, 2025
ae4f582
add quant_input_check
shiyang-weng Jul 17, 2025
469ac50
Merge remote-tracking branch 'origin/main' into wengshiy/qlinear
shiyang-weng Jul 17, 2025
8026306
fix lint
shiyang-weng Jul 17, 2025
f735949
refine ut
shiyang-weng Jul 17, 2025
5803511
remove fp8 dynamic quant ut
shiyang-weng Jul 17, 2025
3e37dea
fix output_scale issue
shiyang-weng Jul 21, 2025
497de92
Merge remote-tracking branch 'origin/main' into wengshiy/qlinear
shiyang-weng Jul 21, 2025
d9ac092
add float8_e4m3fn to dtype_list
shiyang-weng Jul 22, 2025
f88db2d
refine code
shiyang-weng Jul 23, 2025
4f4eb8b
refine code
shiyang-weng Jul 23, 2025
7c3f9f9
fix bugs
shiyang-weng Jul 23, 2025
38de0e9
add comment
shiyang-weng Jul 23, 2025
260f686
Merge remote-tracking branch 'origin/main' into wengshiy/qlinear
shiyang-weng Jul 31, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Loading