Allow non QuantizedTensor layer to set want_requant to get the post lora
calculation stochastic cast down to the original input dtype.
This is then used by the legacy fp8 Linear implementation to set the
compute_dtype to the preferred lora dtype but then want_requant it back
down to fp8.
This fixes the issue with --fast fp8_matrix_mult is combined with
--fast dynamic_vram which doing a lora on an fp8_ non QT model.
Users should either use the cu126 one or the regular one (cu130 at the moment)
The cu128 portable is still included in the latest github release but I will stop including it as soon as it becomes slightly annoying to deal with. This might happen as soon as next week.
Some custom node packs are naughty, and violate the
dont-load-torch-on-load rule. This causes aimdo to lose preference on
its allocator hook on linux.
Go super early on the aimdo first-stage init before custom nodes
are mentioned at all.
Move essentials_category from deprecated/incorrect nodes to their replacements:
- ImageBatch → BatchImagesNode (ImageBatch is deprecated)
- Blur → removed (should use subgraph blueprint)
- GetVideoComponents → Video Slice
Amp-Thread-ID: https://ampcode.com/threads/T-019c8340-4da2-723b-a09f-83895c5bbda5
Implements per-guide attention attenuation via log-space additive bias
in self-attention. Each guide reference tracks its own strength and
optional spatial mask in conditioning metadata (guide_attention_entries).
Comfy Aimdo 0.2.2 moves the cuda allocator hook from the cudart API to
the cuda driver API on windows. This is needed to handle Windows+cu13
where cudart is statically linked.
* utils: dont use comfy sft loader in aimdo fallback
This was going to the raw command line switch and should respect main.py
probe of whether aimdo actually loaded successfully.
* ops: dont use deferred linear load in Aimdo fallback
Avoid changes of behaviour on --fast dynamic_vram when aimdo doesnt work.
* mp: attach re-construction arguments to model patcher
When making a model-patcher from a unet or ckpt, attach a callable
function that can be called to replay the model construction. This
can be used to deep clone model patcher WRT the actual model.
Originally written by Kosinkadink
f4b99bc623
* mp: Add disable_dynamic clone argument
Add a clone argument that lets a caller clone a ModelPatcher but disable
dynamic to demote the clone to regular MP. This is useful for legacy
features where dynamic_vram support is missing or TBD.
* torch_compile: disable dynamic_vram
This is a bigger feature. Disable for the interim to preserve
functionality.
Skip entries in the prompt dict that don't contain a class_type key
in apply_replacements(), preventing crashes on metadata or non-node
entries.
FixesComfy-Org/ComfyUI#12517
* chore: tune CodeRabbit config to limit review scope and disable for drafts
- Add tone_instructions to focus only on newly introduced issues
- Add global path_instructions entry to ignore pre-existing issues in moved/reformatted code
- Disable draft PR reviews (drafts: false) and add WIP title keywords
- Disable ruff tool to prevent linter-based outside-diff-range comments
Addresses feedback from maintainers about CodeRabbit flagging pre-existing
issues in code that was merely moved or de-indented (e.g., PR #12557),
which can discourage community contributions and cause scope creep.
Amp-Thread-ID: https://ampcode.com/threads/T-019c82de-0481-7253-ad42-20cb595bb1ba
* chore: add 'DO NOT MERGE' to ignore_title_keywords
Amp-Thread-ID: https://ampcode.com/threads/T-019c82de-0481-7253-ad42-20cb595bb1ba
On Windows, Python defaults to cp1252 encoding when no encoding is
specified. JSON files containing UTF-8 characters (e.g., non-ASCII
characters) cause UnicodeDecodeError when read with cp1252.
This fixes the error that occurs when loading blueprint subgraphs
on Windows systems.
https://claude.ai/code/session_014WHi3SL9Gzsi3U6kbSjbSb
Co-authored-by: Claude <noreply@anthropic.com>
Integrate comfy-aimdo 0.2 which takes a different approach to
installing the memory allocator hook. Instead of using the complicated
and buggy pytorch MemPool+CudaPluggableAlloctor, cuda is directly hooked
making the process much more transparent to both comfy and pytorch. As
far as pytorch knows, aimdo doesnt exist anymore, and just operates
behind the scenes.
Remove all the mempool setup stuff for dynamic_vram and bump the
comfy-aimdo version. Remove the allocator object from memory_management
and demote its use as an enablment check to a boolean flag.
Comfy-aimdo 0.2 also support the pytorch cuda async allocator, so
remove the dynamic_vram based force disablement of cuda_malloc and
just go back to the old settings of allocators based on command line
input.
Jukka Seppänen
fappaz
Christian Byrne
comfyanonymous
Talmaj
rattus
Reiner "Tiles" Prokein
pythongosssss
vickytsang
comfyanonymous
ComfyUI Wiki
Alexander Piskun
Tavi Halperin
Jedrzej Kosinski
Alexander Brown