hexagon: minor refresh for HMX FA and MM#23796
Merged
max-krasnyansky merged 12 commits intoMay 28, 2026
Merged
Conversation
…nd precomputing fastdiv
This is a bit faster than LUT.
github-actions
Bot
added
ggml
Member
Author
|
@lhez @ggml-org/maintainers can I get some review/approvals please. |
lhez
approved these changes
May 28, 2026
CISC
approved these changes
May 28, 2026
adrianhoehne
pushed a commit
to adrianhoehne/llama.cpp
that referenced
this pull request
May 28, 2026
* hex-fa: clean up qf32/fp32 handling and stride handling * hex-fa: fix corner case fp NAN issues that were cause bad output from gemma4 on v79 * hex-fa: vectorize leftover handling * hex-fa: avoid HVX fallback during token gen HMX has more FP16 compute capacity * hmx-mm: remove dead code * hmx-mm: use fastdiv in x4x2 dequant * hmx-mm: sandwich dequant and scatter to improve perf * hmx-mm: fixed rebase conflicts * hmx-mm: further improve weight dequant by doing early type dispatch and precomputing fastdiv * hmx-mm: an even earlier dispatch for per-type dequant * hmx-mm: dequant linear types like q4_0 and q4_1 without the LUTs This is a bit faster than LUT. * hex-cmake: one more tweak for lto --------- Co-authored-by: Trivikram Reddy <tamarnat@qti.qualcomm.com>
gabe-l-hart
added a commit
to gabe-l-hart/llama.cpp
that referenced
this pull request
May 28, 2026
* origin/master: (32 commits) hexagon: basic/generic op fusion support and RMS_NORM+MUL fusion (ggml-org#23835) mtmd-debug: add color and rainbow mode (ggml-org#23829) mtmd: fix gemma 4 projector pre_norm (ggml-org#23822) opencl: move backend info printing into its own function (ggml-org#23702) ci : run ui publish on ubuntu-slim (ggml-org#23818) ui: fix audio and video modality detection (ggml-org#23756) ci : releases use Github-hosted builds for the UI (ggml-org#23823) app : improve help output (ggml-org#23805) mtmd: n_head_kv defaults to n_head (ggml-org#23782) mtmd: fix gemma 4 audio rms norm eps (ggml-org#23815) ci : change Vulkan builds to Release to reduce ccache (ggml-org#23820) arg: Add LLAMA_ARG_API_KEY_FILE environment variable for --api-key-file (ggml-org#23167) test-llama-archs: fix table format [no release] (ggml-org#23810) ggml: auto apply iGPU flag CUDA/HIP if integrated device (ggml-org#23007) mmvq Optim: add MMVQ_PARAMETERS_TURING(mmvq_parameter_table_id) for … (ggml-org#23729) CUDA: route batch>=4 quantized matmul to MMQ on AMD MFMA hardware (ggml-org#23227) server: minor tweaks to use more cpp features (ggml-org#23785) hexagon: minor refresh for HMX FA and MM (ggml-org#23796) vulkan: fast path for walsh-hadamard transform (ggml-org#23687) chat : add Granite 4.1 chat template (ggml-org#23518) ...
fewtarius
pushed a commit
to fewtarius/llama.cpp
that referenced
this pull request
May 30, 2026
* hex-fa: clean up qf32/fp32 handling and stride handling * hex-fa: fix corner case fp NAN issues that were cause bad output from gemma4 on v79 * hex-fa: vectorize leftover handling * hex-fa: avoid HVX fallback during token gen HMX has more FP16 compute capacity * hmx-mm: remove dead code * hmx-mm: use fastdiv in x4x2 dequant * hmx-mm: sandwich dequant and scatter to improve perf * hmx-mm: fixed rebase conflicts * hmx-mm: further improve weight dequant by doing early type dispatch and precomputing fastdiv * hmx-mm: an even earlier dispatch for per-type dequant * hmx-mm: dequant linear types like q4_0 and q4_1 without the LUTs This is a bit faster than LUT. * hex-cmake: one more tweak for lto --------- Co-authored-by: Trivikram Reddy <tamarnat@qti.qualcomm.com>
turbo-tan
pushed a commit
to turbo-tan/llama.cpp-tq3
that referenced
this pull request
Jun 2, 2026
* hex-fa: clean up qf32/fp32 handling and stride handling * hex-fa: fix corner case fp NAN issues that were cause bad output from gemma4 on v79 * hex-fa: vectorize leftover handling * hex-fa: avoid HVX fallback during token gen HMX has more FP16 compute capacity * hmx-mm: remove dead code * hmx-mm: use fastdiv in x4x2 dequant * hmx-mm: sandwich dequant and scatter to improve perf * hmx-mm: fixed rebase conflicts * hmx-mm: further improve weight dequant by doing early type dispatch and precomputing fastdiv * hmx-mm: an even earlier dispatch for per-type dequant * hmx-mm: dequant linear types like q4_0 and q4_1 without the LUTs This is a bit faster than LUT. * hex-cmake: one more tweak for lto --------- Co-authored-by: Trivikram Reddy <tamarnat@qti.qualcomm.com>
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
4 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
Another pass at improving HMX FA and MM, and FA in general.
This does include a critical fix for Gemma-4 on Hexagon v79 which was broken due to v79 specific issues with handling INF and NaN which was breaking Gemma-4 FA after a certain context size.
The changes do provide a little perf uplift, especially for the Token Gen on older SOCs with fewer HVX threads.
Requirements