AIQB
TutorialsOrdinary

DeepSeek V4.1 Flash on 8 B300: vLLM vs DeepInfer, 600K+ tokens/s

Source: DEV Community·
DeepSeek

Summary

DeepSeek has open-sourced DeepInfer, the engine behind its own production service. We put it head to...
CategoryAI Tutorials & Practice
TierOrdinary
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-459892792fd060748684b888
Read original source ↗More Tutorials

Related stories

Matched by category, entity tags and source

TutorialsOrdinary
Models Know What to Change. But Do They Know What to Leave Alone?
This is a submission for the Kaggle Benchmarking Challenge My first evaluation gave DeepSeek,...
Source: DEV Community · DeepSeek
TutorialsOrdinary
DeepSeek 4.1 Flash Costs $0.003 per Million Tokens. Here Is the Two-Tier Router It Makes Possible.
If you run AI agents on cron jobs the way I do, you already know where the bill comes from. It is not...
Source: DEV Community · DeepSeek
TutorialsOrdinary
Malware asks four AIs before it acts
Malware that has no orders inside: CLOSEDQUORUM asks DeepSeek, Qwen, Mistral and Gemini what to do next. The pattern is no longer in the binary, it is in the outbound traffic.
Source: DEV Community · DeepSeek / Qwen / Gemini
TutorialsOrdinary
SiliconFlow API Review 2026: Setup, Models and Real Pricing
A hands-on SiliconFlow API guide: OpenAI-compatible setup, model catalogue, rate limits and per-token prices vs DeepSeek, Together AI and DeepInfra.
Source: DEV Community · OpenAI / DeepSeek
TutorialsOrdinary
Your system prompt is silently killing your prompt cache
A benchmark on DeepSeek. Moving roughly 30 tokens from the top of a system message to the bottom cut...
Source: DEV Community · DeepSeek
TutorialsOrdinary
Running the 510 GB DeepSeek-V4.1-Flash on an 8 GB GPU — and three bugs that never raise an error
My home machine for local models is modest: an RTX 5060 with 8 GB, a Core Ultra 5 225F, 31 GiB of RAM...
Source: DEV Community · DeepSeek
TutorialsOrdinary
Export ChatGPT, Claude, Gemini, Grok, DeepSeek, Kimi, and Qwen chats to Markdown with Convolvger 0.6.0
If you have ever tried to export a ChatGPT conversation to Markdown, or save a Claude chat as a .md...
Source: DEV Community · ChatGPT / DeepSeek / Qwen
TutorialsOrdinary
Can DeepSeek 4.1 Flash Replace Your $20 Coding Subscription?
A question came up at work recently: can we ditch our $20 monthly coding subscriptions and just use...
Source: DEV Community · DeepSeek
TutorialsOrdinary
Our 3 a.m. batch job was running at Beijing's afternoon peak rate
DeepSeek's API charges two different prices for the same tokens. Which one you pay depends on what...
Source: DEV Community · DeepSeek
TutorialsOrdinary
Test-Time Compute and GRPO in Practice: From PPO to Critic-Free Reinforcement Learning
A deep dive into the paradigm shift from pre-training scaling laws to test-time compute. We deconstruct the mathematical derivation of DeepSeek-R1's Group Relative Policy Optimization (GRPO), critic-free architecture advantages, emergent s…
Source: DEV Community · DeepSeek