AI and Tech Summaries - AI Weekly Malaysia

Summaries

Short AI and tech summaries with source links, signal scores, and why each update matters for builders, founders, and Malaysian tech workers.

Window

Today Yesterday This week Last week This month Last month All time

Showing 1-1 of 1 results

Date	Provider	Score	Summary
20 Oct 2026, 8:00 AM	Hugging Face Blog	7.5	MPS in PyTorch 2.15 The Hugging Face PyTorch team detailed what lands in PyTorch 2.15's MPS backend for Apple Silicon: FP8 (float8_e4m3fn) storage and scaled matmul, a native grouped matmul with a dedicated MoE decoding path, specialized matrix-vector kernels for single-row linear layers, and a softmax over the vocabulary that is about 8x faster. Measured on an M3 Ultra with torch.compile, Qwen3.6-35B-A3B goes from 9.4 to 61.3 tokens/s and LFM2.5-8B-A1B from 23.6 to 123.6 tokens/s versus 2.14, while Wan2.2's tiled VAE video decode drops from a 270 GiB peak to 8 GiB. The release also exposes public MPS streams, adds complex LU and triangular solves plus faster small-matrix inverses and QR on GPU, and raises requirements to macOS 15+ and Python 3.11+; 2.16 is slated to move attention fully onto Metal. Why: If you run local models on a Mac (transformers, diffusers, ComfyUI), the upgrade gate is the decision: PyTorch 2.15 needs macOS 15+ and Python 3.11+, so anyone on macOS 14 or Python 3.10 stays on 2.14 and gets none of the 5-6.5x MoE decode gain. For those who can upgrade, the Wan2.2 VAE number (270 GiB to 8 GiB peak) is the concrete one: video decode that previously needed a datacenter GPU now fits in unified memory, which changes whether local video generation is viable for you at all. pytorch apple-silicon mps local-llm performance fp8

Date

Provider

Score

Summary

20 Oct 2026, 8:00 AM

Hugging Face Blog

7.5

MPS in PyTorch 2.15

The Hugging Face PyTorch team detailed what lands in PyTorch 2.15's MPS backend for Apple Silicon: FP8 (float8_e4m3fn) storage and scaled matmul, a native grouped matmul with a dedicated MoE decoding path, specialized matrix-vector kernels for single-row linear layers, and a softmax over the vocabulary that is about 8x faster. Measured on an M3 Ultra with torch.compile, Qwen3.6-35B-A3B goes from 9.4 to 61.3 tokens/s and LFM2.5-8B-A1B from 23.6 to 123.6 tokens/s versus 2.14, while Wan2.2's tiled VAE video decode drops from a 270 GiB peak to 8 GiB. The release also exposes public MPS streams, adds complex LU and triangular solves plus faster small-matrix inverses and QR on GPU, and raises requirements to macOS 15+ and Python 3.11+; 2.16 is slated to move attention fully onto Metal.

Why: If you run local models on a Mac (transformers, diffusers, ComfyUI), the upgrade gate is the decision: PyTorch 2.15 needs macOS 15+ and Python 3.11+, so anyone on macOS 14 or Python 3.10 stays on 2.14 and gets none of the 5-6.5x MoE decode gain. For those who can upgrade, the Wan2.2 VAE number (270 GiB to 8 GiB peak) is the concrete one: video decode that previously needed a datacenter GPU now fits in unified memory, which changes whether local video generation is viable for you at all.