Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
from
login
Gemlite: Towards Building Custom Low-Bit Fused CUDA Kernels
(
mobiusml.github.io
)
47 points
by
un_ess
on Aug 15, 2024
|
past
|
2 comments
Aana SDK: open-source library for building multimodal AI applications
(
mobiusml.github.io
)
2 points
by
ibuildthings
on July 17, 2024
|
past
|
1 comment
Faster and Smaller Whisper: A Deep Dive into Quantization and Torch Compilation
(
mobiusml.github.io
)
3 points
by
freediver
on June 4, 2024
|
past
Towards 1-bit Machine Learning Models
(
mobiusml.github.io
)
351 points
by
homarp
on March 28, 2024
|
past
|
157 comments
Half-Quadratic Quantization of Large Machine Learning Models
(
mobiusml.github.io
)
1 point
by
Jimmc414
on March 14, 2024
|
past
Half-Quadratic Quantization of Large Machine Learning Models
(
mobiusml.github.io
)
8 points
by
ibuildthings
on Dec 7, 2023
|
past
|
1 comment
Half-Quadratic Quantization of Large Machine Learning Models
(
mobiusml.github.io
)
2 points
by
mobicham
on Dec 7, 2023
|
past
|
1 comment
Low-Rank Pruning of Llama2
(
mobiusml.github.io
)
2 points
by
ibuildthings
on Nov 3, 2023
|
past
|
3 comments
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
