DEV Community

#amd

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Muse Glimmer 30B on Strix Halo: a week of measurements
niclydon profile

Muse Glimmer 30B on Strix Halo: a week of measurements

#ai #llm #opensource #amd
3
Comments 1
19 min read
Modern processors automatically increase their speed, leaving less room for overclocking
hacksgr profile

Modern processors automatically increase their speed, leaving less room for overclocking

#overclocking #amd #ryzenmaster #cpus
Comments
2 min read
The FP8 trap: my GPU bill dropped 47% because the model was printing "!!!!!!"
throttle_pro profile

The FP8 trap: my GPU bill dropped 47% because the model was printing "!!!!!!"

#llm #gpu #mcp #amd
Comments
3 min read
Evaluating Speculative Decoding in vLLM on AMD MI300X GPUs
rammehta1899 profile

Evaluating Speculative Decoding in vLLM on AMD MI300X GPUs

#vllm #amd #mi300x #rocm
Comments
1 min read
AMD Bets $8.2B on World Models and Fei-Fei Li
peremptory profile

AMD Bets $8.2B on World Models and Fei-Fei Li

#amd #aistrategy #hardware #aiinfrastructure
Comments
2 min read
From Naive CUDA to Performance Engineering: My First GPU Matmul Journey
karthikunni profile

From Naive CUDA to Performance Engineering: My First GPU Matmul Journey

#ai #gpu #amd #programming
Comments
3 min read
VLLM_ROCM_USE_AITER=1 Slows Gemma 4 on an AMD MI300X: What the Flag Changes and Why
xbill profile

VLLM_ROCM_USE_AITER=1 Slows Gemma 4 on an AMD MI300X: What the Flag Changes and Why

#gemma #amd #machinelearning #llm
Comments 4
6 min read
The AMD Mini-Challenge 3: citation-by-necessity RAG on ROCm
eterniti profile

The AMD Mini-Challenge 3: citation-by-necessity RAG on ROCm

#amd #rocm #rag #machinelearning
Comments
5 min read
AMD Local LLM Setup on Windows/Linux: ROCm Overrides & Vulkan vs. HIP Benchmarking
xanpavle profile

AMD Local LLM Setup on Windows/Linux: ROCm Overrides & Vulkan vs. HIP Benchmarking

#ai #opensource #amd #python
1
Comments
1 min read
AMD Zen 6 makes Linux's SafeRET mitigation unnecessary
techaiwire profile

AMD Zen 6 makes Linux's SafeRET mitigation unnecessary

#security #linux #hardware #amd
5
Comments
4 min read
Gemma 4 From E2B to 31B on an AMD MI300X: fp8 Overtakes bf16 From 12B Up
xbill profile

Gemma 4 From E2B to 31B on an AMD MI300X: fp8 Overtakes bf16 From 12B Up

#gemma #amd #machinelearning #llm
9
Comments 2
9 min read
Gemma 4 E2B on an AMD MI300X: Which Weight Format Should You Serve?
xbill profile

Gemma 4 E2B on an AMD MI300X: Which Weight Format Should You Serve?

#gemma #amd #machinelearning #llm
8
Comments 4
10 min read
I Tried Getting Closer to the GPU With Triton
karthikunni profile

I Tried Getting Closer to the GPU With Triton

#ai #gpu #nvidia #amd
1
Comments
6 min read
Serving Gemma 4 on an AMD MI300X: What $1.99 an Hour Buys

Real-world benchmarks and MCP tool management tips
xbill profile

Serving Gemma 4 on an AMD MI300X: What $1.99 an Hour Buys

#amd #vllm #rocm #machinelearning
15
Comments 7
9 min read
An MI300X Over MCP: What the Matrix Cores Execute, and What They Don't
xbill profile

An MI300X Over MCP: What the Matrix Cores Execute, and What They Don't

#amd #mcp #rocm #machinelearning
13
Comments 5
20 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.