llama.cpp/ggml/src/ggml-cpu/llamafile
shalinib-ibm e6ec21e62f
ggml-cpu: add always_inline to tinyBLAS_PPC accumulator saves (#20791)
Explicitly mark save_acc and add_save_Acc with always_inline
in tinyBLAS_PPC. This ensures the compiler keeps MMA accumulator
disassembly within kernel's register context, preventing un-necessary
stask spills.

Signed-off-by: Shalini Salomi Bodapati <Shalini.Salomi.Bodapati@ibm.com>
2026-03-21 07:11:45 +08:00
..
sgemm.cpp ggml-cpu: add always_inline to tinyBLAS_PPC accumulator saves (#20791) 2026-03-21 07:11:45 +08:00
sgemm.h Q4/Q8 Tiled Gemm Optimization. (#16999) 2025-12-05 19:41:51 +08:00