vulkan: extend topk_moe fusion to support sqrt(softplus) - #26124
Merged
Conversation
github-actions
Bot
added
Vulkan
0cc4m
approved these changes
Jul 31, 2026
0cc4m
added
the
merge ready
CISC
approved these changes
Aug 1, 2026
kashif
pushed a commit
to kashif/llama.cpp
that referenced
this pull request
Aug 2, 2026
TheTom
pushed a commit
to TheTom/llama-cpp-turboquant
that referenced
this pull request
Aug 3, 2026
belarusian
pushed a commit
to belarusian/llama.cpp
that referenced
this pull request
Aug 4, 2026
smalinin
pushed a commit
to smalinin/llama.cpp
that referenced
this pull request
Aug 4, 2026
Maxritz
pushed a commit
to Maxritz/LLAMA-ALL-INCLUSIVE
that referenced
this pull request
Aug 8, 2026
Maxritz
added a commit
to Maxritz/LLAMA-ALL-INCLUSIVE
that referenced
this pull request
Aug 8, 2026
No shared git history exists with upstream (our root commit is parentless, a fresh source import rather than a real fork/clone), so a normal merge/rebase isn't possible -- cherry-picked commits individually instead, each verified independently. Landed 7 of 8 identified commits; skipped upstream's own Q2_0 (788e07d) since it collides with our already-verified, benchmarked custom Q2_0 (type 42) implementation -- same feature name, two independently-developed and incompatible kernels. - e34e9c6 vulkan: Refactor vk_queue to use per-instance mutexes and unique handles (ggml-org#23570) -- required updating our custom paged-KV/radix Vulkan code (pkv_vulkan_init/pkv_dispatch_init call sites), which accessed the old plain vk_queue struct fields directly. - 27b7fcf vulkan: add iq4_nl support back to FA (ggml-org#24585) - 29f1212 vulkan: Support quantized concat (ggml-org#25684) - 3cb4d39 vulkan: add POOL_1D op (ggml-org#25431) - a329897 vulkan: extend topk_moe fusion to support sqrt(softplus) (ggml-org#26124) - a72c87f vulkan backend ops: implemented GATED_LINEAR_ATTN (ggml-org#25601) - 0756c85 vulkan: fix submission batching size, add debug tools for diagnosing causes of DeviceLost drivers errors (ggml-org#26371) -- AMD-specific driver-timeout workaround, directly relevant to this fork's RDNA4 focus. Verified: full Release build of build-vulkan-rdna4-fresh (0 errors), real model load + inference request through the Vulkan backend produced correct output. docs/ops.md left as the incoming (upstream) version for now since it's auto-generated (scripts/create_ops_docs.py) from real test-backend-ops CSV dumps per backend -- needs a proper regeneration pass, not hand-editing, to reflect our custom ops too. Backup of pre-sync main state: branch + tag pre-upstream-vulkan-sync (pushed to origin). Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
satindergrewal
pushed a commit
to satindergrewal/llama.cpp
that referenced
this pull request
Aug 11, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Overview
Similar fusion to #25896, for dsv4.
I don't have perf results because I think the models are too big for my GPU. But I did verify this kicks in in the backend tests and in test-llama-archs (with some codex fixes to make dsv4 actually run there).
Requirements