Back to article
arXiv

DFlash: Block Diffusion for Flash Speculative Decoding (opens in new tab)

Covered by 4 sources See all sources covering this story including Modal, NVIDIA Technical Blog

Covered in 6 articles

Modal·

Achieve state-of-the-art inference latencies with speculative decoding

Feeds
Modal·

Modal Auto Endpoints: Optimized inference you own

Discussed on Hacker News
Feeds
Modal·

Speculation Is All You Need

Discussed on Hacker News
Feeds
NVIDIA Technical Blog·

Boost Inference Performance up to 15x on NVIDIA Blackwell Using DFlash Speculative Decoding

Feeds
Fergus's blog·

Adaptive speculative decoding: picking draft lengths at runtime

Discussed on Hacker News
Feeds
lmsys.org·

DFlash and Spec V2 Decoding (14 minute read)

Discussed on Hacker News
Feeds

Keyboard Shortcuts

Navigation

Next / previous post
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Discover
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help