llama.cpp

2 posts connected to this tag.

Jul 20, 2026

Qwen3.5 Hybrid Recurrent Attention: How DeltaNet State And Full Attention Share One Decoder

Trace Qwen3.5's hybrid circuit, see how CKE X-ray finds numerical divergence, and separate exact runtime parity from the observed quality of a 0.8B model.

Read post →

Jul 19, 2026

Prefill vs Decode in CKE: Why One Model Needs GEMM, GEMV, and Two Execution Plans

Follow an LLM request from tokenization through prefill, KV-cache construction and decode, then see why CPU projections become GEMM or GEMV and how CKE compares them with llama.cpp.

Read post →

Get my rants delivered to your inbox

I will send new posts as and when I write. No fixed cadence, just engineering notes, rants, and things I am thinking through.

Need an intelligent system to work on real hardware?

Embedded systems · Robotics · Constrained AI · CPU and HPC · Accelerators · Distributed systems

Work With Us / Antshiv Robotics

See engineering services

ShivasNotes

Independent notes on software, systems, AI workflows, robotics, and building Antsand in public.

Qwen3.5 Hybrid Recurrent Attention: How DeltaNet State And Full Attention Share One Decoder

Prefill vs Decode in CKE: Why One Model Needs GEMM, GEMV, and Two Execution Plans

Subscribe

Subscribe to emails from Anthony

Need an intelligent system to work on real hardware?

Embedded systems · Robotics · Constrained AI · CPU and HPC · Accelerators · Distributed systems

ShivasNotes

Read

Support