Merge halo-box/llama.cpp master into strix (2026-09-15) - #64

Merged

dzannotti merged 81 commits into

sync/halo-master-2026-09-15

Sep 17, 2026

Commits on Sep 11, 2026

server: refactor subproc handling (#28555)

ngxson
and
ServeurpersoCom
authored
82d6bb2

Commits on Sep 12, 2026

ggml-webgpu: Update to a recent version of Dawn (#28683)

MendyBerger
and
yomaytk
authored
d3146f2
hexagon: support for multi-device model split (aka row-split) (#28589)

max-krasnyansky
and
alexlu-qc
authored
eafe15a
webgpu: align tensor bindings to the type block size (#28382)
ServeurpersoCom
authored
3f5e94d
opencl: add bin kernel `kernel_gemm_noshuffle_q4_k_f32_32b_trans_ila_a8_bin` (#28677)

shaofeiqi
and
lhez
authored
07fc977
opencl: fix several bugs where the backend aborts (#27630)
wanghqc
authored
8a56aed
server: frame the router child state command as a whole line (#28747)
ServeurpersoCom
authored
c069aa7
rpc : fix linking when compiling with BUILD_SHARED_LIBS=OFF (#28492)
EAddario
authored
f3a33df
syscl : Handle (fail gracefully) unsupported tq1_0 quants (#28681)
mctylr-gh
authored
2a3005c
vendor : update cpp-httplib to 0.56.0 (#28787)
cabelo
authored
718f7b4
server : add missing headers (#28795)
angt
authored
e192abb
ggml-cuda: hip add specific config table for AMD GCN (#27841)
thelittlefireman
authored
c8edceb
server : allow model downloads at model limit fix issue #26809 (#28530)
chenmiaoming
authored
56381e4
ui : add cache (#28802)
angt
authored
3057bb6
cmake: leave the timestamp out of precompiled headers on clang (#28816)
ServeurpersoCom
authored
737e098
jinja : support dot property integer literals (#28817)
CISC
authored
ae9afff
common : implement common_schema internal representation for JSON schemas (#28736)
aldehir
authored
acecd56
common: add LOG_JSON macro to log structured data (#28586)
ngxson
authored
8e33095

Commits on Sep 13, 2026

Commits on Sep 14, 2026

common : move llama_n_rs_seq to before llama_decode (#28749)
danbev
authored
093a2f8
sycl : fix oneDNN scratchpad breaking the pool free order (#28704)
lslusarczyk
authored
661643e
ci : remove gg_sum summary logic (#28857)
ggerganov
authored
15d8f2d
ci : trigger self-hosted CI on changes to ci/run.sh (#28859)
ggerganov
authored
89fe242
ggml-cpu : disable PCH and fix CACHE_LINE_SIZE ambiguity to fix heap corruption (#28882)
ggerganov
authored
2f53959
sycl: rfc: Use radix select for top_k (#28670)

cwriter
and
cwriter
authored
21f6b0d
llama: add Maple 20B-A1B ternary MoE architecture (CPU) (#27000)
AlexGabbia
authored
3d10bcd
tests(s390x): add non-vxe build to tests (#28776)
taronaeo
authored
be2c6d7
models : fix mimo2 swa pattern load (#28865)
CISC
authored
1aca1f9
models : fix incorrect uses of get_key_or_arr (#28868)
CISC
authored
97e4ca7
tests : add fusion baseline README and broaden fusion CI triggers (#28893)
ggerganov
authored
bbdd9f2
ggml : bump version to 0.24.0 (ggml/1627)
ggerganov
committed
eeea731
sync : ggml
ggerganov
committed
d9e03f1
llama.cpp : bump version to 0.4.1 (#28900)
ggerganov
authored
b29c606
scripts: Add script to verify API/ABI compatibility (#28579)
ckastner
authored
dfe4516
cmake : remove precompiled headers (#28892)
danbev
authored
f3a184b
release : added gfx1103 to ubuntu rocm build (#28423)
apparle
authored
b4fa47d
qwen4exp: enable rms_norm + mul fusion (#28896)
am17an
authored
41abbfd
ci : add ubuntu-cuda builds to release (#28186)

ORippler
and
CISC
authored
391fac1
HIP: fattn-mma: use fp32 accumulation on MFMA devices (#28576)
IMbackK
authored
bfdc321
CI: hip-quality-check: ignore spill added in bfdc32183d57f1e35bacf35c47d6311e2028bbbc (#28909)
IMbackK
authored
96ffdc4
ci : reuse build tag name when used instead of safe one (#28911)
CISC
authored
7cf1c54
webui: stop re-probing disabled /tools endpoint on every message (#28646)
geckguy
authored
1bc7a5a

Commits on Sep 15, 2026

cmake : use PROJECT_SOURCE_DIR instead of CMAKE_SOURCE_DIR (#28771)
danbev
authored
69eb250
cuda : enable i16 and i32 for DUP (#28897)
amankarki151
authored
4c9233c
ci : fix android release (#28936)
CISC
authored
987498f
ci: Bump CUDA Windows x64 builds to 13.4.1 (#28930)
shivamkumard-ctrl
authored
0ecb159
metal : add FA kernels for HSK=96, HSV=64 (MiniCPM3) (#28599)
wyanzhao
authored
1e7bcf3
ci: bump kleidiai runners from 22.04 to 24.04 (#28885)
taronaeo
authored
1af6c65
opencl: add generic ssm_scan (#28881)
lhez
authored
6ec1a7e
OpenVINO: optimize stateful decode and GPU MoE inference (#28638)

authored
77d554b
vulkan: support sparse Flash Attention (#28105)
0cc4m
authored
fc82583
models : move build_arch_graph() after graph() template specialization (#28934)
cpeterso
authored
9e71716
cuda: support row-contiguous SUM_ROWS (#26308)
MohamedElashri
authored
5431581
chat : enforce string enums in Qwen XML tool arguments (#26)
arc-uri-el
authored
e20d6f5
rpc : hash-cache only weights (#28789)

authored
7609846
docs: Rule of thumb for AI review time [no ci] (#28945)
JohannesGaessler
authored
6011c34
ci: build MUSA for only 1 arch (#28944)
am17an
authored
d1d3c33
opencl: choose the MoE expert matmul by batch size for speculative decoding/MTP (#27637)

wanghqc
and
lhez
authored
9f31776
HIP: Enable AllReduce for ROCm (#27825)
Stastez
authored
38a5b42
sync upstream llama.cpp commits 2026 09 15 (#28)

authored
e3120a1
--ngram-on-disk and lazymode merge (#29)
dzannotti
authored
77024dd
ggml: recover two upstream commits dropped during the #28 sync (#30)

authored
8a400d0
Record upstream sync (content applied via #28, gaps recovered in #30)
dzannotti
committed
f6a7a6c
docs: add upstream sync procedure (#31)
dzannotti
authored
4bc01d0
Merge halo-box/llama.cpp master into strix-llama.cpp
dzannotti
committed
dced43c

Commits on Sep 17, 2026

Merge strix master (#63) into the halo-box sync

dzannotti
and
claude
committed
82aed60
Merge halo-box/llama.cpp master (#31) into strix-llama.cpp

dzannotti
and
claude
committed
dffbb78