hexagon: add HTP kernel for GGML_OP_GATED_DELTA_NET#5

Closed

wyanzhao wants to merge 16 commits into

hexagon-gated-delta-net

Commits on May 8, 2026

fix script error (#22795sycl : )
arthw
authored
convert : fix RuntimeError when stripping FP8 KV-cache scales (#22818)

pich
and
CISC
authored
opencl: add q4_0 MoE GEMM for Adreno (#22731)

shawngu-quic
and
lhez
authored
ggml: update SCHED_DEBUG output to use ggml_op_desc() (#22825)
max-krasnyansky
authored
vulkan: fix spv shadowing (#22760)
miyanyan
authored
CUDA: lower-case PCI bus id, standardize for ggml (#22820)
JohannesGaessler
authored
webui: Add Import/Export of Settings configuration + improve architecture (#22803)
allozaur
authored
cuda: fuse snake activation (mul, sin, sqr, mul, add) (#22667)

ServeurpersoCom
and
am17an
authored
server: (router) expose child model info from router's /v1/models (#22683)
ngxson
authored
server: support Vertex AI compatible API (#22545)
ngxson
authored
webui: fix LLM title generation for agentic conversations (#22840)
smugman-dot
authored
common : revert reasoning budget +inf logit bias (#22740)
aldehir
authored
model : support Gemma4_26B_A4B_NVFP4 (#22804)

ynankani
and
CISC
authored
common : do not wrap raw strings in schema parser for tagged parsers (#22827)
aldehir
authored
Feature hexagon l2 norm (#22816)

pdhinaka
and
max-krasnyansky
authored
hexagon: add HTP kernel for GGML_OP_GATED_DELTA_NET

wyanzhao
authored and
max-krasnyansky
committed