llama.cpp
Arm AArch64: optimized GEMV and GEMM kernels for q4_0_q8_0, and q8_0_q8_0 quantization
#5780
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
28
Changes
View On
GitHub
Arm AArch64: optimized GEMV and GEMM kernels for q4_0_q8_0, and q8_0_q8_0 quantization
#5780
ggerganov
merged 28 commits into
ggml-org:master
from
Dibakar:aarch64-kernel-opts
cebtenzzre
commented on 2024-02-29
Dibakar
force pushed
2 years ago
akingoverlook
commented on 2024-05-07
akingoverlook
requested changes on 2024-05-07
mofosyne
added
enhancement
mofosyne
added
Review Complexity : Medium
ggerganov
commented on 2024-05-17
github-actions
added
build
github-actions
added
examples
github-actions
added
ggml
Dibakar
force pushed
2 years ago
ggerganov
commented on 2024-06-08
ggerganov
approved these changes on 2024-07-07
Arm AArch64: optimized GEMV and GEMM kernels for q4_0_q8_0, and q8_0_…
002e36ea
Arm AArch64: add optimized GEMV and GEMM asm kernels for q4_0_q8_0 qu…
340ef07f
Arm AArch64: add optimized GEMV and GEMM asm kernels for q4_0_q8_0 qu…
81215ff4
Arm AArch64: add optimized GEMV and GEMM asm kernels for q4_0_q8_0 qu…
6c8d8266
Arm AArch64: add optimized GEMV and GEMM asm kernels for q4_0_q8_0 qu…
43e12974
Arm AArch64: add copyright claim only to ggml-aarch64.cpp and ggml-aa…
441ab649
Arm AArch64: minor code refactoring for rebase
8ee67791
Arm AArch64: minor code refactoring for resolving a build issue with …
a657246d
Arm AArch64: minor code refactoring to split the Q4_0_AARC64 type int…
746b57f4
Arm AArch64: minor code change for resolving a build issue with serve…
5d10c218
retrigger checks
7ac03e5f
Arm AArch64: minor code changes for rebase
e2c1c47f
Arm AArch64: minor changes to skip the pr#7433 vec_dot code for arm c…
79b6cdfe
Arm AArch64: remove stale LLAMA_QKK_64 from CMakeLists.txt and delete…
3c1ad5fe
Arm AArch64: add reference scalar gemm and gemv, and avoid dynamic me…
a7055b7b
Arm AArch64: add multithreaded quantization support for the new types…
cce236bc
Arm AArch64: minor code refactoring
7a706067
Arm AArch64: simplify logic for calling gemm and gemv functions in gg…
ffbfabb5
Arm AArch64: minimize changes in ggml_compute_forward_mul_mat
cbbfd69f
Arm AArch64: minor code refactoring, and add reference scalar code to…
35646445
Arm AArch64: minor code refactoring
110d143e
Arm AArch64: minor code refactoring
4ff0b223
Arm AArch64: minor code refactoring
42724b4d
rebase on the latest master commit 3fd62a6 and adapt to the new direc…
e5f4713d
Dibakar
force pushed
to
e5f4713d
2 years ago
ggerganov
commented on 2024-07-09
Arm AArch64: remove a redundant comment
c2595d0b
Arm AArch64: add pragma in ggml-aarch64.c to turn -Woverlength-string…
a7abb785
Arm AArch64: use __aarch64__ check to guard 64-bit neon kernels
0e84ef1a
Arm AArch64: update docs/build.md README to include compile time flag…
c653eb1f
github-actions
added
documentation
ggerganov
merged
0f1a39f3
into master
2 years ago
Login to write a write a comment.
Login via GitHub
Reviewers
ggerganov
akingoverlook
llamaOmy
cebtenzzre
Assignees
No one assigned
Labels
documentation
enhancement
build
examples
Review Complexity : Medium
ggml
Milestone
No milestone
Login to write a write a comment.
Login via GitHub