Heykuki News

TopNewBestAskShowJobs
TopNewBestAskShowJobs
1.
Ask HN: How to Discover Deep Learning Research Labs?
1 point
bluu00
5 years ago
discuss
2.
How attention sinks keep language models stable (hanlab.mit.edu)
219 points
pr337h4m
10 months ago
36 comments
3.
SVDQuant: 4-Bit Quantization Powers 12B Flux on a 16GB 4090 GPU with 3x Speedup (hanlab.mit.edu)
179 points
lmxyy
2 years ago
65 comments
4.
SVDQuant+NVFP4: 4× Smaller, 3× Faster FLUX with 16-bit Quality on Blackwell GPUs (hanlab.mit.edu)
52 points
lmxyy
a year ago
10 comments
5.
Radial Attention: O(nlogn) Attention for Long Video Generation with 2-4× Speedup (hanlab.mit.edu)
6 points
lmxyy
a year ago
1 comment
6.
RTX 5090 Workstation Configuration Journey (hanlab.mit.edu)
5 points
lmxyy
a year ago
1 comment
7.
TinyChat: Large Language Model on the Edge (hanlab.mit.edu)
2 points
enduku
2 years ago
1 comment
8.
HART: Efficient Visual Generation with Hybrid Autoregressive Transformer (hanlab.mit.edu)
2 points
lnyan
2 years ago
discuss