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
Two Ways to Move Tensors Without Stopping: Inside vLLM's Async GPU Transfer Patterns
Mayank Ketkar
Mayank Ketkar
Mayank Ketkar
Follow
Feb 11
Two Ways to Move Tensors Without Stopping: Inside vLLM's Async GPU Transfer Patterns
#
gpu
#
cuda
#
python
#
machinelearning
2
 reactions
Comments
1
 comment
7 min read
Building an AI App? Here’s the Inference Stack You Actually Need
Sharvari Raut
Sharvari Raut
Sharvari Raut
Follow
Feb 12
Building an AI App? Here’s the Inference Stack You Actually Need
#
gpu
#
opensource
#
ai
#
cloud
1
 reaction
Comments
Add Comment
4 min read
A Taxonomy of GPU Bugs: 19 Defect Classes for CUDA Verification
云微
云微
云微
Follow
Feb 10
A Taxonomy of GPU Bugs: 19 Defect Classes for CUDA Verification
#
ebpf
#
gpu
#
verifier
Comments
Add Comment
42 min read
Compiling the Vision Encoder: Squeezing 3% More Throughput from Qwen3-VL on Hopper GPUs
Mayank Ketkar
Mayank Ketkar
Mayank Ketkar
Follow
Feb 9
Compiling the Vision Encoder: Squeezing 3% More Throughput from Qwen3-VL on Hopper GPUs
#
vllm
#
pytorch
#
gpu
#
machinelearning
Comments
Add Comment
11 min read
How PCIe, NVLink, and NUMA Topology Affect GPU Scheduling Outcomes
Daya Shankar
Daya Shankar
Daya Shankar
Follow
Feb 9
How PCIe, NVLink, and NUMA Topology Affect GPU Scheduling Outcomes
#
gpu
#
cloudpractitioner
#
acecloud
Comments
Add Comment
9 min read
How GPU Cloud Providers Handle Long-Tail Job Backlogs
Daya Shankar
Daya Shankar
Daya Shankar
Follow
Feb 9
How GPU Cloud Providers Handle Long-Tail Job Backlogs
#
cloudpractitioner
#
gpu
#
cloudcomputing
Comments
Add Comment
7 min read
Building Neuro‑OS Desktop: A Lightweight Python Desktop Environment with Adaptive Optimization
cyberenigma-lgtm
cyberenigma-lgtm
cyberenigma-lgtm
Follow
Feb 7
Building Neuro‑OS Desktop: A Lightweight Python Desktop Environment with Adaptive Optimization
#
ai
#
python
#
gpu
#
desktop
Comments
Add Comment
2 min read
The Myth of “Just Add a GPU” in Machine Learning
Siddhartha Reddy
Siddhartha Reddy
Siddhartha Reddy
Follow
Feb 4
The Myth of “Just Add a GPU” in Machine Learning
#
machinelearning
#
python
#
deeplearning
#
gpu
2
 reactions
Comments
Add Comment
3 min read
Optimizing GPU Workload Placement in Kubernetes with NVLink-Aware Scheduling
Lalit Somavarapha
Lalit Somavarapha
Lalit Somavarapha
Follow
Jan 27
Optimizing GPU Workload Placement in Kubernetes with NVLink-Aware Scheduling
#
kubernetes
#
nvidia
#
gpu
#
scheduling
Comments
Add Comment
4 min read
A Universal FPGA Compiler that Understands 42 Programming Languages
Server Serverlesskiy
Server Serverlesskiy
Server Serverlesskiy
Follow
Jan 26
A Universal FPGA Compiler that Understands 42 Programming Languages
#
gpu
#
robotics
#
compiling
#
c
Comments
Add Comment
8 min read
LLMs Can Now Write GPU Kernels That Beat torch.compile
Jaber Jaber
Jaber Jaber
Jaber Jaber
Follow
Jan 23
LLMs Can Now Write GPU Kernels That Beat torch.compile
#
gpu
#
cuda
#
triton
#
llm
Comments
Add Comment
7 min read
Revolution in Voice AI: Natural Conversations with NVIDIA PersonaPlex! - Proje Defteri
Yunus Emre
Yunus Emre
Yunus Emre
Follow
for
Proje Defteri
Jan 27
Revolution in Voice AI: Natural Conversations with NVIDIA PersonaPlex! - Proje Defteri
#
nvidia
#
gpu
#
whisper
#
opensource
2
 reactions
Comments
Add Comment
4 min read
NVIDIA GPU Monitoring: Catch Thermal Throttling Before It Costs You $50k/Year
Manas Sharma
Manas Sharma
Manas Sharma
Follow
Feb 1
NVIDIA GPU Monitoring: Catch Thermal Throttling Before It Costs You $50k/Year
#
devops
#
monitoring
#
gpu
#
observability
3
 reactions
Comments
Add Comment
7 min read
DVTRGA2 The Official Graphics Engine of Neuro‑OS Genesis Enters a New Era
cyberenigma-lgtm
cyberenigma-lgtm
cyberenigma-lgtm
Follow
Feb 11
DVTRGA2 The Official Graphics Engine of Neuro‑OS Genesis Enters a New Era
#
gpu
#
graphics
#
benchmarking
#
cpp
4
 reactions
Comments
Add Comment
2 min read
VHE: GPU-Accelerated Gate-Level Simulation at Zero License Cost
WIOWIZ Technologies
WIOWIZ Technologies
WIOWIZ Technologies
Follow
Jan 16
VHE: GPU-Accelerated Gate-Level Simulation at Zero License Cost
#
dv
#
gpu
#
opensource
#
semiconductor
Comments
Add Comment
2 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