auto-round
[model-free] raise error when ignoring quantized layer, allow special model (deepseekv4.1 engram.embed)
#2631
Merged

[model-free] raise error when ignoring quantized layer, allow special model (deepseekv4.1 engram.embed) #2631

xin3he merged 6 commits into main from xinhe/11-16a
xin3he
xin3he feat: add validation for ignoring quantized NVFP4 layers and support …
9c93217a
xin3he xin3he requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 3 days ago
azure-pipelines
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-11-16
AutoRoundBot
changwangss
AutoRoundBot
xin3he
xin3he feat: add indexed quantized source layer detection and corresponding …
08bdffcf
xin3he
xin3he feat: enhance quantization handling with weight map loading and valid…
062034ae
xin3he Merge branch 'main' into xinhe/11-16a
9a0009a8
AutoRoundBot
azure-pipelines
changwangss
changwangss approved these changes on 2026-11-17
xin3he
xin3he Merge branch 'main' into xinhe/11-16a
6ebe2572
AutoRoundBot
azure-pipelines
xin3he fix: enhance ignored quantized source handling with model type support
bf96da8e
AutoRoundBot
azure-pipelines
AutoRoundBot
xin3he xin3he changed the title feat: add validation for ignoring quantized NVFP4 layers and support for BF16 configuration [model-free] raise error when ignoring quantized layer, allow special model (deepseekv4.1 engram.embed) 1 day ago
xin3he
azure-pipelines
xin3he
azure-pipelines
xin3he xin3he merged 1586bc6f into main 1 day ago
xin3he xin3he deleted the xinhe/11-16a branch 1 day ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone