Skip to content

Conversation

@ZX-ModelCloud
Copy link
Collaborator

No description provided.

Signed-off-by: ZX-ModelCloud <[email protected]>
@Qubitium Qubitium marked this pull request as ready for review September 18, 2025 11:23
@Qubitium Qubitium merged commit ad58827 into main Sep 23, 2025
5 checks passed
Qubitium added a commit that referenced this pull request Sep 23, 2025
* cleanup

Signed-off-by: ZX-ModelCloud <[email protected]>

* fix AWQ marlin quantize and load

Signed-off-by: ZX-ModelCloud <[email protected]>

* Update loader.py

* fix select_quant_linear() with awq marlin

Signed-off-by: ZX-ModelCloud <[email protected]>

* add awq_marlin_repack.cu

Signed-off-by: ZX-ModelCloud <[email protected]>

* call awq_marlin_repack()

Signed-off-by: ZX-ModelCloud <[email protected]>

* add apply_awq_marlin_linear()

Signed-off-by: ZX-ModelCloud <[email protected]>

* move common code to utils/marlin.py

Signed-off-by: ZX-ModelCloud <[email protected]>

* fix awq marlin

Signed-off-by: ZX-ModelCloud <[email protected]>

* cleanup

Signed-off-by: ZX-ModelCloud <[email protected]>

* cleanup

Signed-off-by: ZX-ModelCloud <[email protected]>

* fix marlin forward() with bias

Signed-off-by: ZX-ModelCloud <[email protected]>

* cleanup

Signed-off-by: ZX-ModelCloud <[email protected]>

---------

Signed-off-by: ZX-ModelCloud <[email protected]>
Co-authored-by: Qubitium-ModelCloud <[email protected]>
@CSY-ModelCloud CSY-ModelCloud deleted the zx_fix_AWQ_Marlin branch October 20, 2025 03:21
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants