Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
cuda
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
The sm_120 shared-memory cliff: why FP8 KV cache crashes vLLM on workstation Blackwell
Jahn
Jahn
Jahn
Follow
Aug 25
The sm_120 shared-memory cliff: why FP8 KV cache crashes vLLM on workstation Blackwell
#
cuda
#
llm
#
gpu
#
performance
Comments
Add Comment
3 min read
The Cheapest CUDA GPU on AWS Has an Arm CPU — and You Probably Want the Intel One
xbill
xbill
xbill
Follow
for
AWS Community Builders
Aug 31
The Cheapest CUDA GPU on AWS Has an Arm CPU — and You Probably Want the Intel One
#
aws
#
vllm
#
cuda
#
machinelearning
3
 reactions
Comments
Add Comment
11 min read
Accelerating Physical AI Workloads with NVIDIA CUDA and TensorRT
vmodal_ai
vmodal_ai
vmodal_ai
Follow
Aug 29
Accelerating Physical AI Workloads with NVIDIA CUDA and TensorRT
#
cuda
#
nvidia
#
ai
#
machinelearning
Comments
Add Comment
2 min read
I Built a CUDA Engine That Streams 744B Parameter AI Models on Consumer Hardware
Zero_planck
Zero_planck
Zero_planck
Follow
Jul 28
I Built a CUDA Engine That Streams 744B Parameter AI Models on Consumer Hardware
#
ai
#
cuda
#
opensource
#
machinelearning
2
 reactions
Comments
Add Comment
4 min read
Qwen3-8B on workstation Blackwell: vLLM vs SGLang vs llama.cpp, plus an FP8 pass
Jahn
Jahn
Jahn
Follow
Aug 25
Qwen3-8B on workstation Blackwell: vLLM vs SGLang vs llama.cpp, plus an FP8 pass
#
machinelearning
#
cuda
#
performance
#
llm
2
 reactions
Comments
1
 comment
3 min read
Running Gemma 4 on EC2 G5g: Graviton2 AMD with NVIDIA GPU
xbill
xbill
xbill
Follow
for
Google Developer Experts
Aug 13
Running Gemma 4 on EC2 G5g: Graviton2 AMD with NVIDIA GPU
#
aws
#
vllm
#
cuda
#
machinelearning
13
 reactions
Comments
Add Comment
9 min read
Breaking CUDA's Chains: Open-Source Alternatives for Cross-GPU Performance Optimization
Tamiz Uddin
Tamiz Uddin
Tamiz Uddin
Follow
Jul 14
Breaking CUDA's Chains: Open-Source Alternatives for Cross-GPU Performance Optimization
#
ai
#
breaking
#
cuda
#
chains
Comments
Add Comment
2 min read
Serving Gemma4 with Rust on vLLM 🦀
xbill
xbill
xbill
Follow
for
Google Developer Experts
Aug 14
Serving Gemma4 with Rust on vLLM 🦀
#
rust
#
vllm
#
aws
#
cuda
10
 reactions
Comments
Add Comment
10 min read
Running Gemma 4 on EC2 G5g: Graviton2 AMD with NVIDIA GPU
xbill
xbill
xbill
Follow
for
AWS Community Builders
Aug 13
Running Gemma 4 on EC2 G5g: Graviton2 AMD with NVIDIA GPU
#
aws
#
vllm
#
cuda
#
machinelearning
Comments
Add Comment
9 min read
RTX 5090 survival guide: sm_120, CUDA 12 and 13 side by side, and the xformers trap
Will Kline
Will Kline
Will Kline
Follow
Jul 28
RTX 5090 survival guide: sm_120, CUDA 12 and 13 side by side, and the xformers trap
#
nvidia
#
cuda
#
hardware
#
ai
1
 reaction
Comments
Add Comment
7 min read
GPU-Accelerating MSCRED with CUDA, im2col, GEMM, and a Custom PyTorch Extension
ranjithvutnoor
ranjithvutnoor
ranjithvutnoor
Follow
Aug 5
GPU-Accelerating MSCRED with CUDA, im2col, GEMM, and a Custom PyTorch Extension
#
pytorch
#
cuda
#
machinelearning
#
performance
4
 reactions
Comments
2
 comments
11 min read
Resurrecting Kepler: Getting Modern LLMs Running on a GTX 770 (Kernel 7.x)
skyne
skyne
skyne
Follow
Jun 27
Resurrecting Kepler: Getting Modern LLMs Running on a GTX 770 (Kernel 7.x)
#
cuda
#
linux
#
llm
#
gpu
1
 reaction
Comments
Add Comment
4 min read
I Built Flash Attention From Scratch — Here's What Nobody Tells You About It
JITENDRA KUMAR SINGH
JITENDRA KUMAR SINGH
JITENDRA KUMAR SINGH
Follow
Jun 20
I Built Flash Attention From Scratch — Here's What Nobody Tells You About It
#
showdev
#
machinelearning
#
deeplearning
#
cuda
Comments
Add Comment
2 min read
One RTX 5090 vs a 12-GPU Cluster — Benchmarking a Decade of GPUs on the Same Go Proof
soy
soy
soy
Follow
Jul 18
One RTX 5090 vs a 12-GPU Cluster — Benchmarking a Decade of GPUs on the Same Go Proof
#
gpu
#
benchmark
#
machinelearning
#
cuda
Comments
Add Comment
4 min read
Learn CUDA and GPU programming without owning a GPU
I Want To Learn Programming
I Want To Learn Programming
I Want To Learn Programming
Follow
Jun 9
Learn CUDA and GPU programming without owning a GPU
#
cuda
#
gpu
#
parallel
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