Skip to content

Conversation

@ZX-ModelCloud
Copy link
Collaborator

No description provided.

…"mlp"] tensor

Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
@Qubitium
Copy link
Collaborator

Qubitium commented Nov 4, 2025

@ZX-ModelCloud Let's refractor this into model def. We need this fix for all future moes.

@Qubitium Qubitium mentioned this pull request Nov 4, 2025
ZX-ModelCloud and others added 9 commits November 4, 2025 12:01
Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
…_proj"]

Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
@Qubitium Qubitium changed the title [FIX] AWQ quantization that used the wrong input_feature["mlp"] tensor [FIX] AWQ MoE Nov 4, 2025
Qubitium and others added 7 commits November 4, 2025 14:22
Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
@Qubitium Qubitium merged commit f956309 into main Nov 5, 2025
5 checks passed
@Qubitium Qubitium deleted the zx_fix_qwen2_moe_with_AWQ branch November 5, 2025 14:09
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.

3 participants