|
Getting started with vLLM for a small tool-using AI agent
|
|
1
|
16
|
October 27, 2026
|
|
VLLM_ROCM_USE_AITER=1 makes Gemma 4 12B fp8 slower on MI300X: untuned a8w8 shapes, Triton attention
|
|
5
|
53
|
October 11, 2026
|
|
[Video Tutorial] Using the AMD Developer Cloud in Minutes
|
|
4
|
310
|
October 10, 2026
|
|
Gemma 4 from E2B to 31B on one MI300X: fp8 overtakes bf16 from 12B up
|
|
0
|
29
|
October 9, 2026
|
|
Ten weight formats of Gemma 4 E2B on one MI300X: fp8 is the only one at bf16's pace
|
|
0
|
35
|
October 8, 2026
|
|
GPU Droplet Availability
|
|
0
|
33
|
October 7, 2026
|
|
Optimizing vLLM Inference on AMD GPUs with ROCm and AITER
|
|
0
|
50
|
September 22, 2026
|
|
Which numeric formats an MI300X actually executes — measured on a Developer Cloud droplet
|
|
5
|
102
|
September 18, 2026
|
|
Serving Gemma 4 E2B on one MI300X with vLLM
|
|
0
|
32
|
September 18, 2026
|
|
AMD GPUs not available in certain regions
|
|
1
|
42
|
September 14, 2026
|
|
⚠️ AMD Developer Cloud is in high demand!
|
|
5
|
218
|
September 9, 2026
|
|
Energy per token on Radeon: 8.7× efficiency from batching, and 4 ways to measure it wrong
|
|
1
|
72
|
August 28, 2026
|
|
Fireworks credits
|
|
1
|
117
|
July 27, 2026
|
|
Credit request order for Radeon cloud
|
|
0
|
74
|
July 11, 2026
|
|
Amdgpu VF init fails on managed SR-IOV GPU instance — "Doesn't get ack from pf", REQ_INIT_DATA unsupported, probe fails with -62
|
|
4
|
117
|
May 29, 2026
|
|
How to Get Started on the AMD Developer Cloud
|
|
0
|
142
|
January 12, 2026
|