happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
llama.cpp/ggml/src/ggml-openvino
History
Yu, Zijun 1c0a47a485 Fix --direct-io 0 2026-02-11 10:15:09 +08:00
..
openvino kq_mask naming fix 2026-01-15 14:38:53 -08:00
.clang-format Style: middle ptr and ref align, omit optional struct keyword 2026-01-15 11:27:30 -08:00
CMakeLists.txt Use shared_buffer for GPU NPU; Refactor 2026-01-15 11:39:08 -08:00
ggml-decoder.cpp kq_mask naming fix 2026-01-15 14:38:53 -08:00
ggml-decoder.h Initial stateful graph support 2026-01-15 11:39:08 -08:00
ggml-openvino-extra.cpp Update ggml/src/ggml-openvino/ggml-openvino-extra.cpp 2026-01-15 11:39:08 -08:00
ggml-openvino-extra.h Optimize symmetric quant weight extraction: use single zp 2026-01-15 11:39:08 -08:00
ggml-openvino.cpp Fix --direct-io 0 2026-02-11 10:15:09 +08:00
ggml-quants.cpp Optimize symmetric quant weight extraction: use single zp 2026-01-15 11:39:08 -08:00
ggml-quants.hpp NPU always requant to q4_0_128 2026-01-15 11:39:08 -08:00
utils.cpp Fix llama-bench -p -n where p<=256 2026-02-11 10:15:09 +08:00
utils.h Fix llama-bench -p -n where p<=256 2026-02-11 10:15:09 +08:00