Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
inference
Follow
Hide
Posts
Left menu
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Renting GPUs by the hour in the EU: how to size a card and read the bill
ENTRONYX CLOUD
ENTRONYX CLOUD
ENTRONYX CLOUD
Follow
Nov 18
Renting GPUs by the hour in the EU: how to size a card and read the bill
#
gpu
#
llm
#
inference
#
devops
Comments
Add Comment
5 min read
Moderation
What are the best fal.ai alternatives for model inference?
Viswaretas Kotra
Viswaretas Kotra
Viswaretas Kotra
Follow
Nov 18
What are the best fal.ai alternatives for model inference?
#
ai
#
inference
#
serverless
#
gpu
Comments
Add Comment
8 min read
Moderation
Running a 2.8-trillion-parameter model without a graphics card is possible
Dimitri AIGLE
Dimitri AIGLE
Dimitri AIGLE
Follow
Nov 16
Running a 2.8-trillion-parameter model without a graphics card is possible
#
ai
#
opensource
#
hardware
#
inference
Comments
Add Comment
3 min read
Moderation
How Much GPU Memory Do I Need?
Sachin Kr. Rajput
Sachin Kr. Rajput
Sachin Kr. Rajput
Follow
Nov 16
How Much GPU Memory Do I Need?
#
inference
#
llm
#
gpu
#
machinelearning
Comments
Add Comment
9 min read
Moderation
Why a GPU is still essential, even when a CPU runs 2.8 trillion parameters
Dimitri AIGLE
Dimitri AIGLE
Dimitri AIGLE
Follow
Nov 15
Why a GPU is still essential, even when a CPU runs 2.8 trillion parameters
#
ai
#
hardware
#
gpu
#
inference
Comments
Add Comment
3 min read
Moderation
Benchmarking across some of our published families
Raff Martin (esatapedico)
Raff Martin (esatapedico)
Raff Martin (esatapedico)
Follow
Nov 14
Benchmarking across some of our published families
#
ai
#
inference
#
opensource
#
benchmark
Comments
Add Comment
10 min read
Moderation
What Happens When You Hit Enter?
Konrad Wright
Konrad Wright
Konrad Wright
Follow
Nov 13
What Happens When You Hit Enter?
#
machinelearning
#
llm
#
inference
Comments
Add Comment
5 min read
Moderation
How Many Closed Findings Before You Trust a Routing Change
Alex Chen
Alex Chen
Alex Chen
Follow
Nov 13
How Many Closed Findings Before You Trust a Routing Change
#
llm
#
ai
#
gpu
#
inference
1
reaction
Comments
Add Comment
10 min read
Moderation
Pose Estimation: MediaPipe or YOLOPose for Real-Time Pose Classification?
Sai Prudhvi Neelakantam
Sai Prudhvi Neelakantam
Sai Prudhvi Neelakantam
Follow
Nov 13
Pose Estimation: MediaPipe or YOLOPose for Real-Time Pose Classification?
#
computervision
#
poseestimation
#
realtimeai
#
inference
Comments
Add Comment
7 min read
Moderation
Test-Time Compute vs More Parameters: Where the Inference Budget Actually Goes
gxqwb
gxqwb
gxqwb
Follow
Nov 11
Test-Time Compute vs More Parameters: Where the Inference Budget Actually Goes
#
ai
#
inference
#
reasoning
#
scaling
Comments
Add Comment
5 min read
Moderation
수락 길이는 22.8% 늘었는데 처리량은 14.0%만 늘었습니다: DSpine 카드 수치와 공개 파일 헤더로 투기 디코딩 초안 모델을 읽는 법
Vidraft_lab
Vidraft_lab
Vidraft_lab
Follow
Nov 9
수락 길이는 22.8% 늘었는데 처리량은 14.0%만 늘었습니다: DSpine 카드 수치와 공개 파일 헤더로 투기 디코딩 초안 모델을 읽는 법
#
ai
#
machinelearning
#
llm
#
inference
Comments
Add Comment
3 min read
Moderation
Prefix Caching vs Recomputed Prompts: The Hit-Rate Break-Even
gxqwb
gxqwb
gxqwb
Follow
Nov 8
Prefix Caching vs Recomputed Prompts: The Hit-Rate Break-Even
#
ai
#
inference
#
performance
#
caching
Comments
Add Comment
6 min read
Moderation
The Ridge Dies at 228 Tokens on a 4090, and KV Precision Cannot Save It
Jax Sinclair
Jax Sinclair
Jax Sinclair
Follow
Nov 8
The Ridge Dies at 228 Tokens on a 4090, and KV Precision Cannot Save It
#
hardware
#
performance
#
llm
#
inference
Comments
Add Comment
6 min read
Moderation
Mixture-of-Depths vs Uniform Compute: The Routing Tax on Every Token
gxqwb
gxqwb
gxqwb
Follow
Nov 7
Mixture-of-Depths vs Uniform Compute: The Routing Tax on Every Token
#
ai
#
inference
#
performance
#
gpu
Comments
Add Comment
5 min read
Moderation
12.8x faster for coding agents. At full precision.
Jonathan Murray
Jonathan Murray
Jonathan Murray
Follow
for
Backboard.io
Nov 7
12.8x faster for coding agents. At full precision.
#
ai
#
llm
#
inference
#
agents
1
reaction
Comments
Add Comment
2 min read
Moderation
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account