DEV Community

#cuda

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Gemma 4 in Pure JAX: What Changes Between Turing and Ada, and What Doesn't
xbill profile

Gemma 4 in Pure JAX: What Changes Between Turing and Ada, and What Doesn't

#jax #gemma #cuda #machinelearning
Comments
8 min read
g5g vs g6 for LLM Serving: the Same Code, and 3.7x the Throughput
xbill profile

g5g vs g6 for LLM Serving: the Same Code, and 3.7x the Throughput

#aws #jax #cuda #machinelearning
Comments
6 min read
The Cheapest CUDA GPU on AWS Has an Arm CPU — and You Probably Want the Intel One
xbill profile

The Cheapest CUDA GPU on AWS Has an Arm CPU — and You Probably Want the Intel One

#aws #vllm #cuda #machinelearning
Comments
11 min read
Accelerating Physical AI Workloads with NVIDIA CUDA and TensorRT
vmodal_ai profile

Accelerating Physical AI Workloads with NVIDIA CUDA and TensorRT

#cuda #nvidia #ai #machinelearning
Comments
2 min read
Finding a Random Island with Geometry and CUDA
adilaidev profile

Finding a Random Island with Geometry and CUDA

#gpucomputing #geospatial #cuda #geometry
Comments
4 min read
Installing Rust for vLLM on Graviton: a G5g walk-through 🦀
xbill profile

Installing Rust for vLLM on Graviton: a G5g walk-through 🦀

#rust #vllm #aws #cuda
Comments
10 min read
Running Gemma 4 on EC2 G5g: Graviton2 AMD with NVIDIA GPU
xbill profile

Running Gemma 4 on EC2 G5g: Graviton2 AMD with NVIDIA GPU

#aws #vllm #cuda #machinelearning
Comments
9 min read
Qwen3.8 27B at 256K: 50 TPS on a 24 GB GPU
pich profile

Qwen3.8 27B at 256K: 50 TPS on a 24 GB GPU

#aiinfrastructure #llm #cuda #performance
1
Comments 1
11 min read
Understanding GPU Memory: VRAM, Bandwidth, and Why Your Model Won't Fit
3ni8ma profile

Understanding GPU Memory: VRAM, Bandwidth, and Why Your Model Won't Fit

#gpu #cuda #vram #memory
1
Comments
2 min read
Qwen3-8B on workstation Blackwell: vLLM vs SGLang vs llama.cpp, plus an FP8 pass
conatusai profile
Jahn

Qwen3-8B on workstation Blackwell: vLLM vs SGLang vs llama.cpp, plus an FP8 pass

#machinelearning #cuda #performance #llm
1
Comments 1
3 min read
The sm_120 shared-memory cliff: why FP8 KV cache crashes vLLM on workstation Blackwell
conatusai profile
Jahn

The sm_120 shared-memory cliff: why FP8 KV cache crashes vLLM on workstation Blackwell

#cuda #llm #gpu #performance
Comments
3 min read
I Built a CUDA Engine That Streams 744B Parameter AI Models on Consumer Hardware
zeroextubcollab profile

I Built a CUDA Engine That Streams 744B Parameter AI Models on Consumer Hardware

#ai #cuda #opensource #machinelearning
2
Comments
4 min read
Running Gemma 4 on EC2 G5g: Graviton2 AMD with NVIDIA GPU
xbill profile

Running Gemma 4 on EC2 G5g: Graviton2 AMD with NVIDIA GPU

#aws #vllm #cuda #machinelearning
13
Comments
9 min read
Breaking CUDA's Chains: Open-Source Alternatives for Cross-GPU Performance Optimization
tamizuddin profile

Breaking CUDA's Chains: Open-Source Alternatives for Cross-GPU Performance Optimization

#ai #breaking #cuda #chains
Comments
2 min read
Serving Gemma4 with Rust on vLLM 🦀
xbill profile

Serving Gemma4 with Rust on vLLM 🦀

#rust #vllm #aws #cuda
10
Comments
10 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.