Skip to content

[NPU] Fix MTP draft loading for ModelSlim W8A8 checkpoints: dequantize int8 MTP weights - #37736

Open
Mr-qiji wants to merge 2 commits into
sgl-project:mainfrom
Mr-qiji:fix/npu-mtp-modelslim-w8a8-dequant
Open

Mr-qiji wants to merge 2 commits into
sgl-project:mainfrom
Mr-qiji:fix/npu-mtp-modelslim-w8a8-dequant

Create test_qwen3_5_mtp_w8a8_dequant.py

3605385
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

1 warning
label
succeeded Sep 3, 2026 in 4s