Nov 4, 2026
What CKE Built in October 2026: Speech, Serving, and the Numbers Between
A grounded October CKE recap: speech, serving, numerical parity, and a hands-on look at the LinuxUtilities voice-to-agent prototype.
Read post →Tagged With
43 posts connected to this tag.
Nov 4, 2026
A grounded October CKE recap: speech, serving, numerical parity, and a hands-on look at the LinuxUtilities voice-to-agent prototype.
Read post →
Oct 13, 2026
CKE now serves bounded Qwen Code and Gemma4 agent tasks from generated native CPU bundles. Here is what passed, what failed, and why batching remains a separate gate.
Read post →
Oct 11, 2026
A vision model can return plausible text while taking the wrong path through its image prefix. That is the trap I want CKE's tests to catch. In October, the Gemma4 and multimodal work was le...
Read post →
Oct 11, 2026
I want my Linux workstation to read an agent's answer aloud. Whisper already helps me transcribe my own speech; Kokoro is the other direction. I have been following its path through CKE one ...
Read post →
Oct 11, 2026
When I say I want to run several models across my own machines, it is easy to jump straight to a diagram with six GPUs or a cluster of CPUs. The harder question is what one user request actu...
Read post →
Oct 3, 2026
September was the month C-Kernel-Engine started to feel less like a collection of model demonstrations and more like a system I could keep extending. That is not the same as saying it is fin...
Read post →
Oct 2, 2026
In the last post I stopped at a [36,128] tensor: 36 phonemes, each mapped to a 128-number vector by three small lookup tables plus a normalization. That tensor is where the boring part ends ...
Read post →
Sep 29, 2026
Kokoro's phoneme encoder just took its first concrete step into CKE's generated-C lane. The step is deliberately small: one operation — three embedding tables plus a per-token LayerNorm â€...
Read post →
Sep 27, 2026
I have been working on speech recognition in C-Kernel-Engine for a while. Whisper can transcribe my own videos. The other direction is becoming more interesting to me now: I want my Linux wo...
Read post →
Sep 27, 2026
I Want To Use My Linux Workstation Without Looking At It I have spent a lot of time building software that lets me run AI models on CPUs. Now I want to use some of that work for a more perso...
Read post →Sep 23, 2026
A measured two-CPU investigation of how CKE moved Parakeet and Cohere into generated C, including six complete 42-minute runs, exact cross-host transcripts, performance bottlenecks, and rema...
Read post →Sep 19, 2026
My Ericsson work combined Linux systems programming with a larger router architecture spanning service discovery, IPC, recursive lookup, TCAM, NPUs, DPDK and live forwarding. Those two layer...
Read post →Sep 13, 2026
Run CKE manually or use the included local coding-agent prompt to inspect Linux, install dependencies, execute a small Gemma model, and preserve the evidence.
Read post →Sep 13, 2026
CKE now runs three CPU audio paths on the same 42-minute recording: Whisper is practical and fast, Cohere produces deterministic text and SRT across Intel and AMD, and NVIDIA Parakeet works ...
Read post →
Sep 9, 2026
CKE hardened its evidence and Whisper runtime, culminating in persistent workers that cut a controlled 42:22 transcription from 171.60 to 138.73 seconds without changing retained outputs.
Read post →
Sep 6, 2026
Qwen3.8 Flash Next brought hyper-connections, Per-Layer Embedding, recurrent DeltaNet, query-selected sparse attention and mixed packed experts into one CKE circuit. This is what changed, wh...
Read post →
Sep 5, 2026
Yesterday I recorded the second video in my kernel engineering series. Since C-Kernel-Engine already had Whisper support, I wanted to use it to transcribe my own recording. Not another small...
Read post →Sep 2, 2026
A kernel-by-kernel walkthrough of how C-Kernel-Engine runs Whisper end to end in generated FP32 C: the eight signal-processing frontend kernels that turn a WAV into 1500 tokens, the full sti...
Read post →
Aug 26, 2026
A detailed look at CKE's expanded model-family matrix, what each architecture added to the kernel portfolio, and why support must be reported with an evidence level rather than one generic c...
Read post →
Aug 25, 2026
Two measured Qwen3.8-27B runs used a real 128K prompt on one Ryzen CPU to generate complete technical SVGs, then exposed CKE's next cache, traffic and distributed-computing targets.
Read post →
Aug 23, 2026
Qwen3.8 became an explicit CKE model circuit without a runtime fork or a new arithmetic kernel. Merged Ryzen bring-up and 4,000-step X-Ray certification show what reusable numerical provider...
Read post →
Aug 22, 2026
How CKE moved from token-row prefill sharding to a weight-sharded Qwen3.5 transformer block, what reconstructed correctly, and why one Ryzen still beats the current heterogeneous pair.
Read post →
Aug 22, 2026
A receipt-backed account of CKE's founder-funded Intel and AMD CPU lab, the experiments each node unlocks, and the controlled access path planned for collaborators.
Read post →Aug 21, 2026
CKE is not inference-only. Six DSL hardening PRs taught the compiler to reject quiet boundary mismatches: map interfaces, port-vs-ABI validation, ranked providers, and faithful traces — on...
Read post →Aug 20, 2026
CKE moved a Qwen3-VL OCR path from ~281s to ~76.7s against a llama.cpp baseline of ~55.8s — not a victory lap, a map. Revisited after the harness era: corpus certification, X-Ray parity, a...
Read post →Aug 6, 2026
What actually happens between malloc and the CPU streaming gigabytes: pages, the two kinds of page fault, the TLB, huge pages, and why madvise is advice not a guarantee. A CKE-focused follow...
Read post →Aug 5, 2026
CKE is not inference-only. The v7 training and v8 inference lanes share one compiler-interface discipline.
Read post →Aug 4, 2026
A green CI badge is an argument, not a decoration. CKE's nightly report now captures and publishes its runner's hardware identity, renders it as an amber identity plate, and teaches operator...
Read post →
Aug 2, 2026
The two days after the July books closed The July recap closed its Whisper chapter at a 2.7x gap to whisper.cpp: 1.53–1.58 seconds on the controlled Base fixture against 0.567 seconds for ...
Read post →Aug 1, 2026
A source-linked July recap of 194 PRs and 32 articles: multimodal models, long-context numerical parity, compiler and test hardening, CPU evidence, contributors, and the path toward distribu...
Read post →
Jul 31, 2026
How CKE used exact head parallelism and packed quantized kernels to accelerate Qwen3.6-27B Q4_K_M prefill 2.6x on one 5th Gen Xeon node, while remaining about 1.85x behind llama.cpp.
Read post →
Jul 29, 2026
Follow a real CKE X-Ray investigation from a wrong Qwen3.6 token to a grouped recurrent-topology mismatch, including what passes and what remains open.
Read post →
Jul 28, 2026
Read Kimi K3 from its released config, model code, and technical report: the new kernels, the role of scale and training, and what a distributed CPU runtime would need to implement.
Read post →Jul 26, 2026
An earlier article explained how an audio transformer hears: waveform to frames, frames to log-Mel features, features to encoder states, states to decoded text. This article is the implement...
Read post →
Jul 24, 2026
A closed OpenAI evaluation model compromised Hugging Face, while hosted models later refused forensic evidence. The incident strengthens the case for open weights and practical local CPU AI.
Read post →
Jul 23, 2026
Numerical parity is not one BF16 tolerance. Trace how CKE uses llama.cpp, PyTorch, X-Ray, replay provenance and phase-owned kernel contracts to locate the first divergence.
Read post →
Jul 21, 2026
A source-backed walkthrough of how C-Kernel-Engine brings up GLM4 through model contracts, tensor mapping, pairwise partial RoPE, generated C, parity tools, and explicit evidence boundaries.
Read post →Jul 19, 2026
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 →Jul 14, 2026
A visual, source-linked derivation of Nemotron inference, training forward, backpropagation, and quantization across Mamba2, attention, ReLU2, and routed experts.
Read post →
Jul 13, 2026
How Nemotron mixes recurrent state, attention, dense MLP, and routed experts, and why exact routing becomes a CPU memory and scheduling problem.
Read post →Jul 12, 2026
How Gemma4-VL turns image patches into decoder-width visual tokens, why its vision bridge differs from Qwen3-VL, and how CKE is preparing compatibility.
Read post →Jul 11, 2026
How C-Kernel-Engine represents Gemma4 attention and per-layer RoPE from model metadata through IR, kernel maps, and generated C.
Read post →Jul 7, 2026
A kernel-level reading of DeepSeek-V4: mHC residual lanes, CSA/HCA compressed attention, DSA sparse selection, MoE dispatch, low precision, and what those ideas mean for C-Kernel-Engine.
Read post →I write about the maths, the kernels, and what happens when I try to make them work. Join me for the investigations, including the bits that go wrong.
Get the illustrated field guide by email, followed by engineering notes as I write them.