Sync with upstream ggml-org/master (2026-07-25)#69

Merged

jimw567 merged 180 commits into

jimwu.sync-upstream-20260725

Jul 25, 2026

Commits on Jul 10, 2026

Commits on Jul 11, 2026

opencl: add int8 dp4 dense and MoE prefill optimization for Adreno GPUs (#25537)

wanghqc
and
lhez
authored
Vulkan: route large matmuls to medium tile on Adreno (#24877)
Raman-Raje
authored
ggml : add GGML_OP_LIGHTNING_INDEXER that implements DeepSeek V3.2/V4 lightning indexer (#24231)

fairydreaming
and
sszymczy
authored
server: refactor server_stream (#25541)

ngxson
and
ServeurpersoCom
authored
server: allow stream for exec_shell_command (#25526)
ngxson
authored
DeepseekV4: clear cache only for seq rather than full (#25521)
am17an
authored
cuda: Don't crash when querying memory on device with no free memory. (#25157)
cphlipot
authored
gguf : reject empty metadata keys (#24917)
rohitmahesh1
authored
Fix conditional to display 'LLAMA_SPLIT_MODE_TENSOR not implemented for architecture' message (#24926)
kdkd
authored

Commits on Jul 12, 2026

Commits on Jul 13, 2026

Commits on Jul 14, 2026

Commits on Jul 15, 2026

Commits on Jul 16, 2026

Commits on Jul 17, 2026

Commits on Jul 18, 2026

Commits on Jul 20, 2026

Commits on Jul 21, 2026

Commits on Jul 22, 2026

Commits on Jul 24, 2026

Commits on Jul 25, 2026