]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
ggml: aarch64: implement SVE kernels for q2_k_q8_k vector dot (llama/12064)
authorPrashant Vithule <redacted>
Fri, 28 Feb 2025 07:36:12 +0000 (13:06 +0530)
committerGeorgi Gerganov <redacted>
Tue, 4 Mar 2025 19:24:42 +0000 (21:24 +0200)
commit0fd9c967e2d74131e9cba9bf3ad6b5e78e3de535
tree59c2479b4a1f15d5ea90710c09c0b02ae0f37ab1
parent47a15ccbc5363b0ea2db72013b631d1f4c248808
ggml: aarch64: implement SVE kernels for q2_k_q8_k vector dot (llama/12064)

* Added SVE Support for Q2_K Quantized Models

* Use 4-space indentation in the switch cases

* removed comments lines

* Remove the loop Retain the curly bracess for better understanding of code

* Remove the comment like added for q3_k_q8_k kernel

---------

Co-authored-by: vithulep <redacted>
src/ggml-cpu/ggml-cpu-quants.c