Skip to content

Tags: killian/llama.cpp

Tags

b4393

Toggle b4393's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
vulkan: multi-row k quants (ggml-org#10846)

* multi row k quant shaders!

* better row selection

* more row choices

* readjust row selection

* rm_kq=2 by default

b3602

Toggle b3602's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
flake.lock: Update (ggml-org#9068)

b3488

Toggle b3488's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
ggml: bugfix: fix the inactive elements is agnostic for risc-v vector (

…ggml-org#8748)

In these codes, we want to retain the value that they previously held
when mask[i] is false. So we should use undisturbed. With the default
agnostic policy of rvv intrinsic, these values can be held or be
written with 1s.

Co-authored-by: carter.li <carter.li@starfivetech.com>