]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
ggml : block interleaving support for Q4_K quantization for x86 AVX2 architecture...
authorSrihari-mcw <redacted>
Thu, 20 Mar 2025 11:35:34 +0000 (17:05 +0530)
committerGeorgi Gerganov <redacted>
Thu, 27 Mar 2025 09:06:03 +0000 (11:06 +0200)
commit8058f19d0bb8a995ec95d16c28fc3de41660f19a
tree4c3a6478849eb9e2c38b7e0000ac1294eaaac56f
parentae6a9bb9a58a0f02e4bb60393a65bde407c9e346
ggml : block interleaving support for Q4_K quantization for x86 AVX2 architecture (llama/12332)

* Add block interleaving support for Q4_K quantization

* Remove whitespaces and fix CI/CD issues

* Update pointer of bsums from int16_t to const int16_t

* Add vector version of quantize_q8_K_4x8 function

* Update code formatting based on review comments
ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp