mozempk/ggml-org-llama-cpp-mirror
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-11-10 13:54:54 +01:00
Code Issues Packages Projects Releases Wiki Activity
4,088 Commits 982 Branches 8,450 Tags
18429220bdb344da1bc7df9bc580c7b41b3cd57b
Commit Graph
3 Commits
Author SHA1 Message Date
Eve 18429220bd AVX BF16 and single scale quant optimizations (#10212) 
* use 128 bit loads (i've tried 256->128 to death and its slower)

* double accumulator

* avx bf16 vec dot

* +3% q4_0 inference

* +7% tg +5% pp compared to master

* slower f16c version, kep for reference

* 256b version, also slow. i tried :)

* revert f16

* faster with madd

* split to functions

* Q8_0 and IQ4_NL, 5-7% faster

* fix potential overflow (performance reduced)

* 16 bit add for q4_0 only

* merge
 2024-11-15 12:47:58 +01:00
Charles XuandDiego Devesa 1607a5e5b0 backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels (#9921) 
* backend-cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
 2024-11-15 01:28:50 +01:00
Diego DevesaGeorgi GerganovR0CKSTAR
 		ae8de6d50a ggml : build backends as libraries (#10256) 
* ggml : build backends as libraries

---------

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: R0CKSTAR <xiaodong.ye@mthreads.com>
 2024-11-14 18:04:35 +01:00