Ensure force_patch_weights is set when partially loading/unloading models - #469
Open
blepping wants to merge 1 commit into
Open
Ensure force_patch_weights is set when partially loading/unloading models#469blepping wants to merge 1 commit into
blepping wants to merge 1 commit into
Conversation
blepping
force-pushed
the
fix_partially_load_unload
branch
from
July 26, 2026 19:48
e913a8a to
3b4b1ad
Compare
ChrisColeTech
added a commit
to ChrisColeTech/ComfyUI-GGUF-Loader
that referenced
this pull request
Aug 12, 2026
Cherry-pick production fixes from city96/ComfyUI-GGUF open PRs: - city96#472 dequant device-constant cache (major LTX/sampling speedup) - city96#433 IQ1/IQ2/IQ3 torch dequant (extra TE quants) - city96#470 QK-norm .scale→.weight (silent NaN/black Flux-compat) - city96#467 dequant bare nn.Parameters (LTX learnable_registers) - city96#392 lumina2/zimage pad token shape fix - city96#456/city96#468 GGMLTensor dtype + dequantize() for core cast path - city96#461 WeightAdapter-aware move_patch_to_device - city96#469 force_patch on partial load/unload - city96#440/city96#436 mistral3 TE, city96#438 qwen35, qwen2 allowlist - city96#473 partial: Qwen3-VL deepstack mmproj map for MiniMax H3 TE Skipped mega/draft rewrites (city96#459, full city96#473 LazyGGUFReader, city96#336 Triton). See PR_BACKPORT.md for the full matrix.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The custom
GGUFModelPatchersetsforce_patch_weightsto the load method so ComfyUI won't try to create low-VRAM patches for LoRAs, etc. However, it doesn't set that parameter for the partial load/unload methods (which default toforce_patch_weights=False). This results in ComfyUI trying to create model weight functions to apply the LoRAs.With the way the ops and patcher are set up in the official repo, those weight functions get ignored. However, we can skip the overhead of having ComfyUI create patches that are never going to get applied. You can confirm that ComfyUI is creating those weight functions that will never be applied since the log output dumps the low-VRAM patch count when the model gets loaded.