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
Deploying DeepSeek V3 (LLM) Using SGLang
Sanskriti Harmukh
Sanskriti Harmukh
Sanskriti Harmukh
Follow
for
Vultr
Aug 12
Deploying DeepSeek V3 (LLM) Using SGLang
#
ai
#
llm
#
gpu
#
docker
5
 reactions
Comments
1
 comment
2 min read
What Changes in an Agent's Planning Behaviour After a Model Migration
Multigrid
Multigrid
Multigrid
Follow
Aug 12
What Changes in an Agent's Planning Behaviour After a Model Migration
#
ai
#
debugging
#
llm
#
machinelearning
Comments
1
 comment
5 min read
Moderating Large-Volume User Content: Batch LLM Cost Estimates and Token Counting
SvenNilsson228
SvenNilsson228
SvenNilsson228
Follow
Aug 12
Moderating Large-Volume User Content: Batch LLM Cost Estimates and Token Counting
#
python
#
llm
#
contentmoderation
Comments
Add Comment
7 min read
Zod Schemas as Output Contracts
Multigrid
Multigrid
Multigrid
Follow
Aug 12
Zod Schemas as Output Contracts
#
ai
#
javascript
#
tutorial
#
llm
1
 reaction
Comments
Add Comment
7 min read
Batch LLM Jobs vs Realtime APIs — Bulk Summarization Cost Attribution
HoldenFox8476
HoldenFox8476
HoldenFox8476
Follow
Aug 12
Batch LLM Jobs vs Realtime APIs — Bulk Summarization Cost Attribution
#
batch
#
llm
#
backend
Comments
Add Comment
6 min read
Compaction turns your agent's decisions into folklore — here's the fix
Linford Reyes
Linford Reyes
Linford Reyes
Follow
Aug 12
Compaction turns your agent's decisions into folklore — here's the fix
#
llm
#
python
#
ai
#
opensource
Comments
Add Comment
2 min read
The reward signal is the bottleneck, not the model
Aamer Mihaysi
Aamer Mihaysi
Aamer Mihaysi
Follow
Aug 12
The reward signal is the bottleneck, not the model
#
ai
#
llm
#
agents
Comments
Add Comment
3 min read
Run forty experiments against one eval set and you will find an improvement that is not there
Maya Andersson
Maya Andersson
Maya Andersson
Follow
Aug 12
Run forty experiments against one eval set and you will find an improvement that is not there
#
llm
#
statistics
#
datascience
#
testing
Comments
Add Comment
4 min read
Time to First Token vs Tokens per Second
Multigrid
Multigrid
Multigrid
Follow
Aug 12
Time to First Token vs Tokens per Second
#
ai
#
devops
#
llm
#
machinelearning
Comments
Add Comment
5 min read
What to Expect From Pure CPU-Only Local Inference
Multigrid
Multigrid
Multigrid
Follow
Aug 12
What to Expect From Pure CPU-Only Local Inference
#
ai
#
llm
#
machinelearning
#
programming
Comments
Add Comment
5 min read
12 Agentic Harness Patterns
Akash Thakur
Akash Thakur
Akash Thakur
Follow
Aug 12
12 Agentic Harness Patterns
#
ai
#
agents
#
llm
#
mcp
Comments
2
 comments
6 min read
Approval Testing for Prompt Output
Multigrid
Multigrid
Multigrid
Follow
Aug 12
Approval Testing for Prompt Output
#
ai
#
llm
#
machinelearning
#
programming
Comments
1
 comment
4 min read
Choosing the Right LLM-as-a-Judge: A Practical Guide with Model Recommendations
Sanjeev Kumar
Sanjeev Kumar
Sanjeev Kumar
Follow
Aug 12
Choosing the Right LLM-as-a-Judge: A Practical Guide with Model Recommendations
#
ai
#
llm
#
evaluation
Comments
Add Comment
7 min read
Truncated Output: Diagnosing an Unfinished Answer
Multigrid
Multigrid
Multigrid
Follow
Aug 12
Truncated Output: Diagnosing an Unfinished Answer
#
ai
#
llm
#
machinelearning
#
programming
Comments
Add Comment
6 min read
Circuits: Reverse-Engineering One Behaviour End to End
Multigrid
Multigrid
Multigrid
Follow
Aug 12
Circuits: Reverse-Engineering One Behaviour End to End
#
ai
#
machinelearning
#
llm
#
programming
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