Commit Graph
3 Commits
Author SHA1 Message Date
90c26fcd4b Vulkan: add hoisting support for row IDs and expert count in shaders (#26686)
* vulkan: add hoisting support for row IDs and expert count in shaders

* use hoisted row ids in coopmat2

* vulkan: address review feedback on count_experts
- use vk_op_count_experts_push_constants instead of a raw uint vector
- apply the fastdiv trick to the ne00 div/mod in count_experts
- compute the per-expert offsets with subgroupExclusiveAdd when the
  device supports it, keeping the serial path as fallback
- document the data_d layout and the hoisted_row_id_words bound
- drop a leftover debug print in ggml_vk_matmul_id

* vulkan: use init_pushconst_fastdiv for count_experts push constants

* vulkan: refine comments for row ID hoisting and data layout in count_experts shader

* Whitespace

---------

Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
2026-08-28 16:52:49 +02:00
ravel7524andGitHub e3471b3e73 Remove case for GGML_TYPE_Q4_K in mvvq.cu (#23528) 2026-06-09 07:46:23 +02:00
ravel7524andGitHub b39a7bf1b0 ggml-cuda: tune RDNA3 Q6_K MMVQ nwarps (#23349) 2026-05-20 09:52:21 +08:00