41554 blogs · 4,417,066 posts Claim your blog

Record · corpus.blog/posts/01a087c4-2fc4-71ce-9431-5e373c859cce

Optimizing Transformer Model Serving Parameters – An Apple Silicon GPU Case Study

pinglin.tw · published 11 July 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at pinglin.tw Wayback capture

0blogs citing

First cited: —
Most recent: —
Rank this month: not ranked
Links from this post: 13
Words captured: 3,689

Cited by

No blog we hold has cited this post yet.

Links from this post

Link

Host

https://github.com/Blaizzy/mlx-vlm

github.com

https://kipp.ly/p/transformer-inference-arithmetic

kipp.ly

https://jax-ml.github.io/scaling-book/inference/

jax-ml.github.io

https://arxiv.org/abs/2403.02310

arxiv.org

https://docs.vllm.ai/en/stable/configuration/optimization/

docs.vllm.ai

https://github.com/Blaizzy/mlx-vlm/issues/1559

github.com

https://arxiv.org/abs/2401.09670

arxiv.org

https://arxiv.org/abs/2311.18677

arxiv.org

https://groq.com/blog/llama-4-now-live-on-groq-build-fast-at-the-lowest-cost-without-compromise

groq.com

Blackwell Breaks the 1,000 TPS/User Barrier With Meta’s Llama 4 Maverick Read at the source ↗

developer.nvidia.com

https://github.com/Blaizzy/mlx-vlm/blob/main/docs/usage.md

github.com

https://groq.com/blog/the-groq-lpu-explained

groq.com

https://www.phison.com/en/aidaptiv-plus-ai-data-storage-solution

phison.com