issues
search
HanGuo97
/
flute
Fast Matrix Multiplications for Lookup Table-Quantized LLMs
https://arxiv.org/abs/2407.10960
Apache License 2.0
187
stars
6
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Update citation.
#13
radi-cho
opened
5 hours ago
0
Trying to build docker container
#12
bekzod
opened
3 days ago
1
Fixed abstract impl for abitrary input dimensions.
#11
BlackSamorez
closed
1 week ago
0
Unknown quantization method: flute
#10
Mr-nnng
closed
1 month ago
6
[FEATURE REQUEST] Support for 6-bit and 8-bit codebooks
#9
BlackSamorez
opened
2 months ago
3
Add learnable scales functionality.
#8
radi-cho
closed
2 months ago
0
Error in flute.utils.pack
#7
KenRanmzes
closed
2 days ago
4
Some questions about kernel
#6
lswzjuer
opened
3 months ago
7
pip install flute-kernel
#5
LiMa-cas
closed
3 months ago
11
Implementation and performance on CPU's
#4
vineel96
closed
3 months ago
7
[Feature Request] Adding Support For cu12.1, RTX4090
#3
telegraph-pole-head
closed
3 months ago
5
Only CUDA devices are supported, but got: {device} ({device.type})
#2
LiMa-cas
closed
4 months ago
13
How to build flute from scratch?
#1
LeiWang1999
closed
4 months ago
4