Skip to content

[pull] master from Comfy-Org:master#692

Merged
pull[bot] merged 4 commits intocode:masterfrom
Comfy-Org:master
Mar 18, 2026
Merged

[pull] master from Comfy-Org:master#692
pull[bot] merged 4 commits intocode:masterfrom
Comfy-Org:master

Conversation

@pull
Copy link

@pull pull bot commented Mar 18, 2026

See Commits and Changes for more details.


Created by pull[bot] (v2.0.0-alpha.4)

Can you help keep this open source service alive? 💖 Please sponsor : )

kijai and others added 4 commits March 17, 2026 20:20
This weight init process is fully shadowed be the weight load and
doesnt work in dynamic_vram were the weight allocation is deferred.
…12809)

On Apple Silicon, `vram_state` is set to `VRAMState.SHARED` because
CPU and GPU share unified memory. However, `text_encoder_device()`
only checked for `HIGH_VRAM` and `NORMAL_VRAM`, causing all text
encoders to fall back to CPU on MPS devices.

Adding `VRAMState.SHARED` to the condition allows non-quantized text
encoders (e.g. bf16 Gemma 3 12B) to run on the MPS GPU, providing
significant speedup for text encoding and prompt generation.

Note: quantized models (fp4/fp8) that use float8_e4m3fn internally
will still fall back to CPU via the `supports_cast()` check in
`CLIP.__init__()`, since MPS does not support fp8 dtypes.
@pull pull bot locked and limited conversation to collaborators Mar 18, 2026
@pull pull bot added the ⤵️ pull label Mar 18, 2026
@pull pull bot merged commit b941913 into code:master Mar 18, 2026
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants