Commit Graph

3 Commits

Author SHA1 Message Date
Jeff Bolz c342c3b93d
vulkan: fix non-contig rope (#19299) 2026-02-05 08:38:59 +01:00
Jeff Bolz 10dc500bdb
vulkan: handle rope with large number of rows (#18306) 2025-12-26 16:53:46 +01:00
Jeff Bolz b4e335d8dc
vulkan: fuse rms_norm + mul + rope (+ view + set_rows) (#16977)
This change combines the rms_norm+mul and rope+view+set_rows fusions to
allow fusing the whole sequence together. This comes up in Qwen3, Bailing,
and some other models.
2025-11-08 08:52:15 +01:00