Skip to content

[pull] master from ggml-org:master#823

Merged
pull[bot] merged 4 commits intoLongLeCE:masterfrom
ggml-org:master
Jan 28, 2026
Merged

[pull] master from ggml-org:master#823
pull[bot] merged 4 commits intoLongLeCE:masterfrom
ggml-org:master

Conversation

@pull
Copy link

@pull pull bot commented Jan 28, 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 : )

kpouget and others added 4 commits January 28, 2026 17:49
Deduplication here relied on the fact that vulkan would return unique
UUID for different physical GPUs. It is at the moment not always the case.
On Mac Pro 2019 running Mac OS, with 2 Vega II Duo cards (so, 4 GPU total),
MotlenVK would assign same UUID to pairs of GPUs, unless they
are connected with Infinity Fabric.

See more details here: KhronosGroup/MoltenVK#2683.

The right way is to fix that in MoltenVK, but until it is fixed,
llama.cpp would only recognize 2 of 4 GPUs in such configuration.

The deduplication logic here is changed to only filter GPUs if UUID is
same but driver is different.
…ng/array) by filters/tests (#19147)

* undefined is treated as iterable (string/array) by filters

`tojson` is not a supported `undefined` filter

* add tests

* add sequence and iterable tests

keep it DRY and fix some types
@pull pull bot locked and limited conversation to collaborators Jan 28, 2026
@pull pull bot added the ⤵️ pull label Jan 28, 2026
@pull pull bot merged commit 60368e1 into LongLeCE:master Jan 28, 2026
7 checks passed
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.

4 participants