you'll know more about inference than 90% of people if you fully understand this article
this is only the first resource in the ai performance engineering repo btw.
imagine the ball knowledge in the other ones
we launched the most comprehensive ai performance engineering repo in the world last week
now we'll be posting every single resource
this is Wafer's ai performance engineering series
save this as your starting point. links in thread 🧵
part 1: "All About Transformer Inference" from How To Scale Your Model.
- the authors cover the computations, memory traffic, and serving decisions behind transformer inference:
- arithmetic intensity of linear layers and attention across prefill and decode.
- kv cache sizing by layer count, kv heads, head dimension, sequence length, and precision.
- the compute/hbm bandwidth crossover and how batch size and quantization shift it.
- decode latency and throughput bounds from parameter bytes, kv bytes, and hardware bandwidth.
- weight reuse through batching and diminishing throughput gains as kv traffic grows.
- gqa, kv quantization, and PagedAttention, including the memory costs each addresses.
- model sharding, kv placement, and collective communication overhead.
- continuous batching, prefix caching, and disaggregated prefill/decode.
the worked problems connect model dimensions to deployment decisions like memory capacity, workload distribution, and expected performance under the stated assumptions.
we're hosting poker night with @Cloudflare next week in nyc.
we have nyc's most promising builders and founders joining. spots are limited.
date: sept 14, 2026
time: 8pm - 12am
link in thread
#waflare iykyk
Join @wafer_ai and @Cloudflare for poker, drinks, and friendly competition in NYC!!
NYC's most promising builders and founders in the same room. Spots are limited.
🗓️ Date: September 14, 2026
🕗 Time: 8PM - 12AM
Registration link in thread 🧵
#waflare 🧇 🫶 ☁️ iykyk
Join @wafer_ai and @Cloudflare for poker, drinks, and friendly competition in NYC!!
We have NYC's most promising builders and founders joining. Spots are limited.
🗓️ Date: September 14, 2026
🕗 Time: 8PM - 12AM
Registration link in thread 🧵
#waflare 🧇 🫶 ☁️ iykyk