HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
61.
▲
The LLM Engine Advisor
modal.com
discuss
a year ago
pierremenard
4 points
62.
▲
Linear Programming for Fun and Profit
modal.com
discuss
a year ago
sebg
4 points
63.
▲
Modal is GA and raised a 16M Series A
modal.com
discuss
3 years ago
stevekrouse
4 points
64.
▲
Keeping 20k GPUs Healthy
modal.com
1 comment
5 months ago
birdculture
3 points
65.
▲
Agents need good developer experience too
modal.com
1 comment
7 months ago
birdculture
3 points
66.
▲
Speculation Is All You Need
modal.com
discuss
3 hours ago
birdculture
3 points
67.
▲
Speculation Is All You Need
modal.com
discuss
21 hours ago
birdculture
3 points
68.
▲
Speculation Is All You Need
modal.com
discuss
2 days ago
birdculture
3 points
69.
▲
Making FlashAttention-4 faster for inference
modal.com
discuss
10 days ago
birdculture
3 points
70.
▲
How to Achieve Truly Serverless GPUs
modal.com
discuss
a month ago
birdculture
3 points
71.
▲
Accelerating AI research that accelerates AI research
modal.com
discuss
4 months ago
tosh
3 points
72.
▲
Keeping 20k GPUs Healthy
modal.com
discuss
5 months ago
aburan28
3 points
73.
▲
Keeping 20k GPUs Healthy
modal.com
discuss
5 months ago
birdculture
3 points
74.
▲
Keeping 20k GPUs Healthy
modal.com
discuss
5 months ago
birdculture
3 points
75.
▲
Host overhead is killing your inference efficiency
modal.com
discuss
6 months ago
birdculture
3 points
76.
▲
Agents need good developer experience too
modal.com
discuss
7 months ago
birdculture
3 points
77.
▲
Host overhead is killing your inference efficiency
modal.com
discuss
7 months ago
birdculture
3 points
78.
▲
Host overhead is killing your inference efficiency
modal.com
discuss
7 months ago
charles_irl
3 points
79.
▲
One second voice-to-voice latency with just open models
modal.com
discuss
7 months ago
birdculture
3 points
80.
▲
1 second voice-to-voice latency with all open models
modal.com
discuss
8 months ago
birdculture
3 points
81.
▲
Modal's $87M Series B
modal.com
discuss
9 months ago
stevekrouse
3 points
82.
▲
Inside vLLM: Anatomy of a High-Throughput LLM Inference System
modal.com
discuss
9 months ago
birdculture
3 points
83.
▲
The LLM Engineer's Almanac
modal.com
discuss
a year ago
birdculture
3 points
84.
▲
LLM Engine Advisor
modal.com
discuss
a year ago
pierremenard
3 points
85.
▲
Linear Programming for Fun and Profit
modal.com
discuss
a year ago
gk1
3 points
86.
▲
I paid for the whole GPU, I am going to use the whole GPU
modal.com
discuss
a year ago
birdculture
3 points
87.
▲
Checkpoint/restore for sub-second container startup
modal.com
discuss
a year ago
birdculture
3 points
88.
▲
GPU Glossary
modal.com
discuss
a year ago
anjneymidha
3 points
89.
▲
GPU Glossary
modal.com
discuss
2 years ago
abhi9u
3 points
90.
▲
How to catch cryptominers using syscall signatures
modal.com
discuss
2 years ago
thundergolfer
3 points
More