issues
search
SNU-ARC
/
any-precision-llm
[ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs
MIT License
83
stars
3
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
No real speedup from any-precision-llm kernels
#7
pgimenes
opened
2 months ago
2
Question regarding 2-bit quantization
#6
jusjinuk
closed
2 months ago
3
2-bit dequant kernel
#5
fwtan
closed
3 months ago
2
Why is 2-bit quantization not supported by the kernel?
#4
hmarkc
closed
4 months ago
1
No speedup from quantization
#3
jiwonsong-dev
closed
4 months ago
4
TODO - 2024 March
#2
SyphonArch
closed
6 months ago
0
Gemma-7B Perplexity Issue
#1
SyphonArch
closed
9 months ago
1