Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
gpu
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Nvidia GreenBoost Lets You Fake More VRAM — And It Actually Kind of Works
TechPulse Lab
TechPulse Lab
TechPulse Lab
Follow
Mar 29
Nvidia GreenBoost Lets You Fake More VRAM — And It Actually Kind of Works
#
nvidia
#
opensource
#
ai
#
gpu
Comments
Add Comment
4 min read
Boost Local LLMs: TurboQuant KV Cache, Fast Cold Starts, & Rust GPU Dev
soy
soy
soy
Follow
Mar 28
Boost Local LLMs: TurboQuant KV Cache, Fast Cold Starts, & Rust GPU Dev
#
gpu
#
ai
#
performance
Comments
Add Comment
4 min read
Fix Zombie VRAM: Clear GPU Memory Without Rebooting
Jakson Tate
Jakson Tate
Jakson Tate
Follow
Mar 28
Fix Zombie VRAM: Clear GPU Memory Without Rebooting
#
linux
#
gpu
#
docker
#
devops
1
 reaction
Comments
Add Comment
4 min read
I shipped Google's TurboQuant as a vLLM plugin 72 hours after the paper — here's what nobody else tested
Alberto Nieto
Alberto Nieto
Alberto Nieto
Follow
Mar 27
I shipped Google's TurboQuant as a vLLM plugin 72 hours after the paper — here's what nobody else tested
#
ai
#
python
#
machinelearning
#
gpu
2
 reactions
Comments
Add Comment
3 min read
Local LLM vs Claude for Coding: I Benchmarked a $500 GPU Against Cloud AI [2026]
Kunal
Kunal
Kunal
Follow
Mar 27
Local LLM vs Claude for Coding: I Benchmarked a $500 GPU Against Cloud AI [2026]
#
localllm
#
gpu
#
benchmarking
#
claude
Comments
Add Comment
8 min read
Local LLM Power-Ups: Voxtral TTS, TurboQuant, & Sub-Second Cold Starts
soy
soy
soy
Follow
Mar 27
Local LLM Power-Ups: Voxtral TTS, TurboQuant, & Sub-Second Cold Starts
#
gpu
#
ai
#
performance
Comments
Add Comment
3 min read
Compressed VLM inference from a single Containerfile — turboquant-vllm v1.1
Alberto Nieto
Alberto Nieto
Alberto Nieto
Follow
Mar 28
Compressed VLM inference from a single Containerfile — turboquant-vllm v1.1
#
python
#
vllm
#
gpu
#
containers
1
 reaction
Comments
Add Comment
2 min read
vLLM On-Demand Gateway: Zero-VRAM Standby for Local LLMs on Consumer GPUs
soy
soy
soy
Follow
Mar 26
vLLM On-Demand Gateway: Zero-VRAM Standby for Local LLMs on Consumer GPUs
#
vllm
#
llm
#
gpu
#
python
1
 reaction
Comments
Add Comment
4 min read
Local LLM Unleashed: Faster Inference, Instant Starts, & Open TTS
soy
soy
soy
Follow
Mar 26
Local LLM Unleashed: Faster Inference, Instant Starts, & Open TTS
#
gpu
#
ai
#
performance
Comments
Add Comment
4 min read
I Tried Speculative Decoding on RTX 4060 8GB — Every Config Was Slower Than Baseline
plasmon
plasmon
plasmon
Follow
Mar 25
I Tried Speculative Decoding on RTX 4060 8GB — Every Config Was Slower Than Baseline
#
llm
#
gpu
#
benchmark
#
ai
1
 reaction
Comments
Add Comment
8 min read
Local LLM Security Criticals, Rust on GPU, & Deep Dive into PTX Optimization
soy
soy
soy
Follow
Mar 24
Local LLM Security Criticals, Rust on GPU, & Deep Dive into PTX Optimization
#
gpu
#
ai
#
performance
Comments
Add Comment
3 min read
Building a Cost-Effective Local AI Server in 2026: Proxmox, PCIe Passthrough, and Surviving the GPU Shortage
GA HANG LAM
GA HANG LAM
GA HANG LAM
Follow
Mar 24
Building a Cost-Effective Local AI Server in 2026: Proxmox, PCIe Passthrough, and Surviving the GPU Shortage
#
ai
#
devops
#
gpu
#
tutorial
Comments
Add Comment
4 min read
Introducing vMetal: Run Your GPU Data Center Like a Hyperscaler
vCluster
vCluster
vCluster
Follow
Mar 23
Introducing vMetal: Run Your GPU Data Center Like a Hyperscaler
#
vcluster
#
vmetal
#
gpu
#
kubernetes
Comments
Add Comment
4 min read
I Rented Out My GPU for Passive Income — Here’s What Happened After My First Week
Sam Hartley
Sam Hartley
Sam Hartley
Follow
Mar 21
I Rented Out My GPU for Passive Income — Here’s What Happened After My First Week
#
gpu
#
passiveincome
#
ai
#
selfhosted
Comments
Add Comment
4 min read
Running a 4-Agent AI Fleet on a Single NVIDIA RTX 3060 Ti
ppcvote
ppcvote
ppcvote
Follow
Mar 20
Running a 4-Agent AI Fleet on a Single NVIDIA RTX 3060 Ti
#
nvidia
#
gpu
#
rtx3060ti
#
ollama
1
 reaction
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