DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
End-to-End Observability for vLLM and TGI: from DCGM to Tokens

End-to-End Observability for vLLM and TGI: from DCGM to Tokens

Comments
13 min read
AI 週報 — 2026-05-15 to 2026-05-22 | 當 IPO 傳聞撞上 27 萬人部署規模

AI 週報 — 2026-05-15 to 2026-05-22 | 當 IPO 傳聞撞上 27 萬人部署規模

Comments
3 min read
Your No-Code AI Agent Has a Memory Problem

Your No-Code AI Agent Has a Memory Problem

1
Comments
2 min read
We Connected an LLM to a 12-Year-Old Codebase. Here's What Broke.

We Connected an LLM to a 12-Year-Old Codebase. Here's What Broke.

Comments
5 min read
Stop your AI trading agent from hallucinating technical analysis

Stop your AI trading agent from hallucinating technical analysis

Comments
2 min read
How to Stop Evaluating LLM Outputs by Gut Feel

How to Stop Evaluating LLM Outputs by Gut Feel

Comments
4 min read
Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift

Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift

1
Comments
5 min read
X's Feed Ranking Algorithm: How Grok Ranks 500M Posts in 200ms

X's Feed Ranking Algorithm: How Grok Ranks 500M Posts in 200ms

Comments
8 min read
The Request Is the Wrong Unit of Scale for LLMs on Kubernetes

The Request Is the Wrong Unit of Scale for LLMs on Kubernetes

Comments
12 min read
Redacting PII in LLM Traces Without Losing Debuggability

Redacting PII in LLM Traces Without Losing Debuggability

Comments
6 min read
Stop Using Raw Vector Search: Implement GraphRAG with Spring AI and Neo4j

Stop Using Raw Vector Search: Implement GraphRAG with Spring AI and Neo4j

Comments
2 min read
Lenovo's AI Host P7: 190 TOPS, 30W, 122B Models — Too Good to Be True?

Lenovo's AI Host P7: 190 TOPS, 30W, 122B Models — Too Good to Be True?

Comments
3 min read
Lookspan: local-first observability for AI agents

Lookspan: local-first observability for AI agents

Comments
1 min read
How Markus Builds AI Teams That Actually Ship — Not Just Chat

How Markus Builds AI Teams That Actually Ship — Not Just Chat

Comments
5 min read
Meet Deliberation: 400+ models is easy, knowing which ones earn a place is hard.

Meet Deliberation: 400+ models is easy, knowing which ones earn a place is hard.

4
Comments
11 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.