BestHub
Sign in
Tagged articles

ROCm

6 articles · Page 1 of 1
Architecture Digest
Architecture Digest
Oct 5, 2026 · Artificial Intelligence

Redis Creator's DwarfStar: Specialized Local Inference Engine for DeepSeek V4 & GLM 5

DwarfStar is a specialized local inference engine by Redis creator antirez, optimized exclusively for DeepSeek V4, GLM 5, and Qwen3.8 Flash Next models across Metal, CUDA, and ROCm platforms, achieving 790 tokens/s prefill on M5 Max and 126 aggregated tokens/s on 8×L40S, with built-in coding agent and HTTP server.

CUDADeepSeek-V4DwarfStar
0 likes · 16 min read
Redis Creator's DwarfStar: Specialized Local Inference Engine for DeepSeek V4 & GLM 5
AI Engineering
AI Engineering
Jul 21, 2026 · Artificial Intelligence

Unsloth Adds AMD Support: Train LLMs on 3 GB VRAM GPUs

Unsloth now supports AMD GPUs with custom ROCm‑optimized Triton kernels, delivering up to double the training speed and 70% lower memory usage, enabling over 500 LLMs to be trained on as little as 3 GB VRAM and providing detailed performance benchmarks on MI300X.

AMDGPULLM
0 likes · 5 min read
Unsloth Adds AMD Support: Train LLMs on 3 GB VRAM GPUs
21CTO
21CTO
Jan 26, 2026 · Artificial Intelligence

What’s New in PyTorch 2.10? Deep Dive into GPU and CUDA Enhancements

PyTorch 2.10 introduces extensive upgrades for AMD ROCm, Intel XPU, and NVIDIA CUDA, adds new Torch XPU APIs, expands Python 3.14 support, and brings performance‑focused improvements such as fused kernels and enhanced quantization, all available via the official GitHub release.

CUDAGPUPyTorch
0 likes · 4 min read
What’s New in PyTorch 2.10? Deep Dive into GPU and CUDA Enhancements