llama.cpp
CUDA: refactor and optimize IQ MMVQ
#8215
Merged

CUDA: refactor and optimize IQ MMVQ #8215

JohannesGaessler
JohannesGaessler CUDA: refactor and optimize IQ MMVQ
ec15f4d5
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
airMeng
JohannesGaessler
JohannesGaessler uint -> uint32_t
0480dab4
mofosyne mofosyne added Review Complexity : High
slaren
JohannesGaessler
slaren
JohannesGaessler
JohannesGaessler __dp4a -> ggml_cuda_dp4a
a92595aa
JohannesGaessler remove MIN_CC_DP4A checks
78754008
JohannesGaessler change default
df9e9c9f
JohannesGaessler
slaren
slaren approved these changes on 2024-06-30
JohannesGaessler try CI fix
30f85eba
the-crypt-keeper
the-crypt-keeper
JohannesGaessler JohannesGaessler merged cb5fad4c into master 1 year ago
duaneking
JohannesGaessler
smcnally
smcnally
JohannesGaessler
smcnally
smcnally
JohannesGaessler
smcnally
JohannesGaessler

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone