Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
llm
Follow
Hide
Posts
Left menu
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
TitanCore Core-1 – Trillion-parameter LLM training infra in C++/CUDA with ZeRO-3
Sarkar-AGI
Sarkar-AGI
Sarkar-AGI
Follow
May 22
TitanCore Core-1 – Trillion-parameter LLM training infra in C++/CUDA with ZeRO-3
#
showdev
#
cpp
#
llm
#
performance
Comments
Add Comment
1 min read
Building and Running Llama.cpp on an Air-Gapped Mac
SomeOddCodeGuy
SomeOddCodeGuy
SomeOddCodeGuy
Follow
May 18
Building and Running Llama.cpp on an Air-Gapped Mac
#
ai
#
cpp
#
llm
#
opensource
Comments
Add Comment
3 min read
AIMO: AI Mention Optimization — The Discipline of Being Recommended by AI Assistants
Septim Labs
Septim Labs
Septim Labs
Follow
May 17
AIMO: AI Mention Optimization — The Discipline of Being Recommended by AI Assistants
#
ai
#
llm
#
marketing
#
product
Comments
Add Comment
6 min read
从 pip install 到生产部署:AI 自愈 Agent 10 分钟上线指南
correctover
correctover
correctover
Follow
Jun 21
从 pip install 到生产部署:AI 自愈 Agent 10 分钟上线指南
#
llm
#
ai
#
python
#
tutorial
Comments
Add Comment
2 min read
Multi-Agent Kill Switch: Why Stopping the Orchestrator Doesn't Stop the Swarm
Logan
Logan
Logan
Follow
for
Waxell
May 18
Multi-Agent Kill Switch: Why Stopping the Orchestrator Doesn't Stop the Swarm
#
ai
#
agents
#
architecture
#
llm
1
reaction
Comments
1
comment
11 min read
GroundedQL: a semantic compiler for natural-language Postgres analytics
Alex
Alex
Alex
Follow
Jun 10
GroundedQL: a semantic compiler for natural-language Postgres analytics
#
python
#
postgres
#
opensource
#
llm
Comments
Add Comment
2 min read
llama.cpp Optimizations & New Qwopus3.5-9B GGUF Model Boost Local AI Performance
soy
soy
soy
Follow
May 17
llama.cpp Optimizations & New Qwopus3.5-9B GGUF Model Boost Local AI Performance
#
ai
#
llm
#
selfhosted
Comments
Add Comment
3 min read
Why I used three different critic roles instead of one (and what the eval taught me)
Bohyeon Jang
Bohyeon Jang
Bohyeon Jang
Follow
May 31
Why I used three different critic roles instead of one (and what the eval taught me)
#
llm
#
python
#
ai
#
evaluation
Comments
2
comments
6 min read
Fitting LLM Reply Suggestions Into Every Provider's Prompt Cache — Without Structured Output
shinji shimizu
shinji shimizu
shinji shimizu
Follow
May 31
Fitting LLM Reply Suggestions Into Every Provider's Prompt Cache — Without Structured Output
#
llm
#
ai
#
rust
#
webdev
Comments
1
comment
4 min read
High-Value If, Low-Value Foreach: Why Agents Trade in Judgment Structures, Not Models
suhui
suhui
suhui
Follow
May 18
High-Value If, Low-Value Foreach: Why Agents Trade in Judgment Structures, Not Models
#
ai
#
agents
#
llm
#
mcp
2
reactions
Comments
Add Comment
23 min read
Tackle High Token Usage with GraphRAG
Apoorva Sachan
Apoorva Sachan
Apoorva Sachan
Follow
May 17
Tackle High Token Usage with GraphRAG
#
devchallenge
#
llm
#
performance
#
rag
1
reaction
Comments
Add Comment
4 min read
Why you still do not trust your AI's memory
Todd Hendricks
Todd Hendricks
Todd Hendricks
Follow
Jun 21
Why you still do not trust your AI's memory
#
agents
#
ai
#
llm
#
rag
1
reaction
Comments
Add Comment
3 min read
How to build a production RAG pipeline in Python (without a vector database)
Ayi NEDJIMI
Ayi NEDJIMI
Ayi NEDJIMI
Follow
May 22
How to build a production RAG pipeline in Python (without a vector database)
#
python
#
ai
#
llm
#
tutorial
1
reaction
Comments
Add Comment
5 min read
Como treinei uma IA de suporte com histórico real de atendimento: da conversa bruta ao RAG em produção
Gabriel Brocco de Oliveira
Gabriel Brocco de Oliveira
Gabriel Brocco de Oliveira
Follow
May 21
Como treinei uma IA de suporte com histórico real de atendimento: da conversa bruta ao RAG em produção
#
ai
#
rag
#
llm
#
datascience
1
reaction
Comments
1
comment
11 min read
Stop Burning Cash on Long-Context RAG: Ephemeral Prompt Caching with Spring AI and JTokkit
Machine coding Master
Machine coding Master
Machine coding Master
Follow
May 31
Stop Burning Cash on Long-Context RAG: Ephemeral Prompt Caching with Spring AI and JTokkit
#
java
#
ai
#
llm
#
systemdesign
Comments
1
comment
2 min read
👋
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