torch's MPS backend has no fp8 casts, so the eager W4A8 dequant path
raises "Undefined type Float8_e4m3fn" on s_rel.float() and no
asym_w4a8_int8 model can load. Convert the group scale at load time;
fp32 is the only other dtype the eager backend declares for s_rel.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KcrQ3SfeW47jxhsyt6KXuQ
Add a ModelAttentionBackend node to manually select the attention for models in the workflows. Currently supports pytorch attention or comfy kitchen attention.
Add --use-ck-attention to enable comfy kitchen attention as the default attention backend for all models (might break some).
This avoids name collision (circular imports) for external custom nodes,
for which the comfy path is pushed into sys.path so Python's own logging module
is shadowed otherwise.
fixes: #15229
This priority scheme was broken in the case where you have pin
registration exhaustion while loading a VBAR that gets a big evicition.
The weight would stay in the loaded set but inherit the MRU priority
against other workflow models WRT pin registration which leads to async
offload without pinning.
Fix by universally promiting active pin registration above workflow
pins without concern for the weights/weights-loaded split. This diverges
from the actual budgeting where the split still makes sense.
Changes:
Remove sequential scan hint
Prefer NVML pressure on windows
Add async malloc clamp option (unused by comfy so far)
Workaround AMD windows GPU virtual address space leak
The largest change is the NVML pressure, which works around a cuMemGetInfo
drift from actual VRAM in some circumstances.
Windows has proven this logic works for a long time and there are
corner cases where this materialization actual consumes real RAM
on linux.
Its not as bad as the original windows commit charge surge, but
its still a detectable transient leak. So simplify and unify.
Some long running chaos testing on a 512GB RAM RTX6000 pro showed that this
is a little bit too low for common template workflows switching around. The
original number was just a guess from me, so go with the scientific result
instead.
These were alll non-dynamic (some non-ModelPatcher) code path calling
FreeMemory for management requiring up-front memory freeing. Convert it
to dynamic to avoid legacy free behaviour mixing into otherwise
dynamic workflows.
Florian Agsteiner
scriptease
comfyanonymous
Jukka Seppänen
Alexis Rolland
blepping
endman100
rattus
rivadart
Oliver Freyermuth
Barish Ozbay