[pull] master from ggml-org:master#523

Merged

pull[bot] merged 9 commits intosyther-labs:masterfrom

ggml-org:master

Aug 13, 2025

Commits on Aug 13, 2025

ggml-rpc: chunk send()/recv() to avoid EINVAL for very large tensors over RPC (macOS & others) (#15188)

Tak-RS
and
Shinnosuke Takagi
authored
ci : add copilot-setup-steps.yml (#15214)
CISC
authored
CUDA: Optimize `reduce_rows_f32` kernel, leading up to 25x perf improvement on kernel-level and 10% perf increase for Gemma3n (#15132)
ORippler
authored
ggml : repack block_iq4_nlx8 (#14904)
ggerganov
authored
ci : add more python requirements to copilot-setup-steps (#15289)
CISC
authored
ci : Added CI with RISC-V RVV1.0 Hardware (#14439)

alitariq4589
and
akifejaz
authored
server : filter out harmony thought messages (#15278)
aldehir
authored
common : add --override-tensor-draft, --cpu-moe-draft and --n-cpu-moe-draft parameters (#15191)

authored
ggml : update `ggml_rope_multi` (#12665)

foldl
and
ggerganov
authored