Commits

Commits on Aug 11, 2026

spec : update speculative-simple (#26904)
ggerganov
authored
f785fc9
chat : tighten bare function parsing for Qwen models (#26793)
aldehir
authored
ba360ef
ci : add windows-rocm to check-release (#26897)
CISC
authored
70dfba5
imatrix.cpp: Move finite check and only check touched experts (#26861)
bartowski1182
authored
38406d5
requirements: use stable torch packages on s390x (#26864)
nikwen
authored
2468576
convert : keep quantization scales for nemotron --mtp export (#26903)
ynankani
authored
5d16e81
Dflash support for nemotron-3.5 (#26905)

lnigam
and
CISC
authored
cc078b4
mtmd: support pocket-tts (#26871)

ngxson
and
ServeurpersoCom
authored
6e62ba5
ui: fix context gauge for single-model usage (#25738)
intel00000
authored
8d274dd
ci: hip-quality-check: update vgpr spill ignore list (#26859)
IMbackK
authored
7044859
model-conversion : use save_output_data for causual embeddings [no ci] (#26890)
danbev
authored
1138b85
tests : fix running server tests on windows (#26889)
ggerganov
authored
9afff1b
llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

authored
153d324
tests : clean-up server test, use `tests.sh` in ci (#26886)
ggerganov
authored
b3df572
tests : disable backend sampler hip multi output (#26878)

jimw567
and
Jim Wu
authored
4801e3c
model : fix SWA not being enabled for EXAONE 4.5 (#26848)
junmo-kim
authored
14e78dd
common/peg : suppress incomplete escape sequences (#26780)
aldehir
authored
48d22e2
ggml-webgpu: fix CI errors from #25025 and #25262 (#26566)
yomaytk
authored
84f7129

Commits on Aug 10, 2026