DEV Community

#cuda

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Gemma 4 on a Tesla T4: QAT Weights Decode 1.79x Faster Than bf16
xbill profile

Gemma 4 on a Tesla T4: QAT Weights Decode 1.79x Faster Than bf16

#gemma #vllm #cuda #machinelearning
1
Comments
9 min read
Same nvJPEG2000, different numbers: timer boundaries and frames in flight
fastvideo profile

Same nvJPEG2000, different numbers: timer boundaries and frames in flight

#cuda #gpu #performance #cpp
Comments
13 min read
Exploring Result Visibility of Fixed-Latency Instructions on the SM120 Architecture
comradepenguin1917 profile

Exploring Result Visibility of Fixed-Latency Instructions on the SM120 Architecture

#cuda #nvidia #gpu
1
Comments
10 min read
Nvidia Just Let Rust Into CUDA. Here's Why That's a Bigger Deal Than It Sounds
ashraf_chowdury09 profile

Nvidia Just Let Rust Into CUDA. Here's Why That's a Bigger Deal Than It Sounds

#rust #ai #cuda #programming
1
Comments
5 min read
CUDA Rust: two native tracks, not a wrapper over C++
jtorchia profile

CUDA Rust: two native tracks, not a wrapper over C++

#english #rust #cuda #gpuprogramming
1
Comments
5 min read
Gemma 4 on an 2021 4 GB Laptop GPU: QAT Takes It From 9.5 GiB to 1.6
xbill profile

Gemma 4 on an 2021 4 GB Laptop GPU: QAT Takes It From 9.5 GiB to 1.6

#gemma #llamacpp #mcp #cuda
10
Comments 3
13 min read
Reverse-Engineering NVIDIA: Modifying a CUDA binary
stjepan86 profile

Reverse-Engineering NVIDIA: Modifying a CUDA binary

#nvidia #gpu #cuda #hex
Comments
4 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
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
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
3
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
5
Comments 2
6 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
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
3
Comments
11 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.