On AMD APUs (and other integrated GPUs) the "VRAM" reported by
torch.cuda.mem_get_info() is the GTT/shared aperture carved out of host
RAM, not a dedicated board. ComfyUI starts such devices in NORMAL_VRAM and
later sums device VRAM plus system RAM when sizing the model-load budget,
so on a UMA part the same physical RAM is counted twice and the inflated
budget triggers HIGH_VRAM / gpu-only placement that OOMs the shared pool.
Detecting integrated GPUs alone is not enough: integrated parts vary widely
in how memory is split. Some (large BIOS UMA carveout, e.g. Strix Halo)
report most memory as dedicated mem_info_vram_total, where HIGH_VRAM is
right; others report a small VRAM carveout with the bulk in GTT, where
SHARED is right. Demoting every integrated GPU to SHARED would regress the
dedicated-heavy configs.
Key the demotion on the amdgpu mem_info_vram_total vs mem_info_gtt_total
ratio: only when an integrated GPU's shared (GTT) pool is at least as large
as its dedicated VRAM do we switch it to VRAMState.SHARED. Dedicated-heavy
integrated parts and discrete GPUs keep NORMAL_VRAM. When the sysfs totals
cannot be read (e.g. NVIDIA Tegra, which has no dedicated VRAM) the device
is treated as shared-heavy, matching its true unified memory.
Fixes#14274
Signed-off-by: liminfei-amd <91481003+liminfei-amd@users.noreply.github.com>
* mm: split off registration helper to doer and headroom calc
* pinned_memory: implement registration comfy side
Move away from Aimdo buffer registrations which seem fraught with
danger and do it comfy side. Just start with the basic move.
* pinned_memory: do registrations as portable memory
* pinned_memory: discard async errors on registration fail
Like the good ol days.
* pinned_memory: implement abs shortfall retry
If pinned registration happens to fail despite the previous budget
ensures, consider the allocation shortfall, ensure it again, and
try again. This allows comfy pins to interoperate with other software
that might be doing substantive pinning.
* fix (MultiGPU): prevent freeze on manual abort when using MultiGPU CFG Split
Problem:
Upon manual abort application hangs indefinitely.
`InterruptProcessingException` inherits from `BaseException` and bypasses MultiGPU's worker error handling block so thread dies silently, leaving the main thread waiting forever for `result_q.get()`
Fix:
Catch `comfy.model_management.InterruptProcessingException` instead of `Exception` so it's caught and passed back via `result_q` to unblock the main thread when manual abort signal fires.
* oops
liminfei-amd
comfyanonymous
Terry Jia
Alexander Piskun
rattus
Jukka Seppänen
Alexis Rolland
Comfy Org PR Bot
Daxiong (Lin)
Yousef R. Gamaleldin
comfyanonymous
Quasar of Mikus
person4268
vidigoat
savvadesogle