Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
llm
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
KVQuant: Run 70B LLMs on 8GB RAM with 4-bit KV Cache Quantization
Aman Sachan
Aman Sachan
Aman Sachan
Follow
Apr 30
KVQuant: Run 70B LLMs on 8GB RAM with 4-bit KV Cache Quantization
#
python
#
llm
#
quantization
#
optimization
Comments
Add Comment
1 min read
Securing Agentic Workflows: A Deterministic 'Human-in-the-Loop' Pattern for LLMs
Badri C
Badri C
Badri C
Follow
Apr 30
Securing Agentic Workflows: A Deterministic 'Human-in-the-Loop' Pattern for LLMs
#
agents
#
architecture
#
llm
#
security
Comments
Add Comment
5 min read
I just wanted to chat with my Raspberry Pi.
Grega Snoj
Grega Snoj
Grega Snoj
Follow
May 4
I just wanted to chat with my Raspberry Pi.
#
ai
#
python
#
raspberrypi
#
llm
Comments
Add Comment
9 min read
Introducing KORA: Open-Source AI Orchestration for Task Graphs
Krako Labs
Krako Labs
Krako Labs
Follow
Jun 3
Introducing KORA: Open-Source AI Orchestration for Task Graphs
#
showdev
#
ai
#
llm
#
opensource
2
 reactions
Comments
1
 comment
2 min read
Fix Your Prompt Structure Before You Touch Your Infrastructure
Parag Darade
Parag Darade
Parag Darade
Follow
Apr 30
Fix Your Prompt Structure Before You Touch Your Infrastructure
#
ai
#
llm
#
rag
#
machinelearning
Comments
Add Comment
4 min read
The AI Tasks Developers Trust And the Ones They Double-Check
preeti deshmukh
preeti deshmukh
preeti deshmukh
Follow
Jun 3
The AI Tasks Developers Trust And the Ones They Double-Check
#
ai
#
llm
#
productivity
#
softwaredevelopment
Comments
Add Comment
11 min read
27/30 Days System Design Questions!
Joud Awad
Joud Awad
Joud Awad
Follow
Jun 2
27/30 Days System Design Questions!
#
systemdesign
#
distributedsystems
#
llm
#
rag
1
 reaction
Comments
4
 comments
2 min read
I measured MCP vs a CLI for agent search. The MCP used 17x more tokens per call.
ARY RABELO
ARY RABELO
ARY RABELO
Follow
Jun 2
I measured MCP vs a CLI for agent search. The MCP used 17x more tokens per call.
#
mcp
#
ai
#
typescript
#
llm
11
 reactions
Comments
2
 comments
6 min read
Why File-to-Markdown Conversion Is Becoming an AI Input Layer
dengkui yang
dengkui yang
dengkui yang
Follow
Apr 30
Why File-to-Markdown Conversion Is Becoming an AI Input Layer
#
markitdown
#
llm
#
ai
Comments
1
 comment
7 min read
Function-calling eval was a 2024 problem. Tool-using agents are the 2026 one.
Nikhil Pareek
Nikhil Pareek
Nikhil Pareek
Follow
Jun 3
Function-calling eval was a 2024 problem. Tool-using agents are the 2026 one.
#
ai
#
llm
#
agents
#
testing
1
 reaction
Comments
Add Comment
5 min read
Running 35B–400B LLMs on a GPU-less Cluster to Mine 10,000 Papers — and the 4 Bugs That Almost Ruined the Data
byeongsoo kang
byeongsoo kang
byeongsoo kang
Follow
Jun 3
Running 35B–400B LLMs on a GPU-less Cluster to Mine 10,000 Papers — and the 4 Bugs That Almost Ruined the Data
#
llm
#
machinelearning
#
python
#
infrastructure
1
 reaction
Comments
Add Comment
9 min read
I Compressed GPT-2 to Run on an Arduino
Aman Sachan
Aman Sachan
Aman Sachan
Follow
Apr 30
I Compressed GPT-2 to Run on an Arduino
#
llm
#
embedded
#
tinyml
#
python
Comments
Add Comment
1 min read
Agent Series (11): A2A Protocol — How Agents Collaborate with Each Other
WonderLab
WonderLab
WonderLab
Follow
Jun 3
Agent Series (11): A2A Protocol — How Agents Collaborate with Each Other
#
agents
#
llm
#
opensource
#
multiagent
Comments
Add Comment
5 min read
TurboQuant on a MacBook Pro, part 2: perplexity, KL divergence, and asymmetric K/V on M5 Max
Christopher Maher
Christopher Maher
Christopher Maher
Follow
Apr 29
TurboQuant on a MacBook Pro, part 2: perplexity, KL divergence, and asymmetric K/V on M5 Max
#
ai
#
llm
#
kubernetes
#
opensource
Comments
Add Comment
8 min read
Why I'm Building a Local-First AI Coding Workspace (And How Behavioral Routing Makes It Work)
Eli Hadam Zucker
Eli Hadam Zucker
Eli Hadam Zucker
Follow
Apr 29
Why I'm Building a Local-First AI Coding Workspace (And How Behavioral Routing Makes It Work)
#
ai
#
rust
#
llm
#
webdev
Comments
Add Comment
6 min read
đź‘‹
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