New Action 3

Oct 20, 2026

Why 4-Bit Quantization Is King: Understanding Q4_K, MXFP4, and NVFP4

Why four-bit quantization matters: follow packed weights through scales, CPU registers, AVX-512, and GEMM, then compare Q4_K, MXFP4, NVFP4, and CKE implementation PRs.

Read post →

Jul 23, 2026

What Numerical Parity Actually Requires: BF16, Quantization, ISA Drift And CKE X-Ray

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 14, 2026

Nemotron Kernels From Inference To Backpropagation

A visual, source-linked derivation of Nemotron inference, training forward, backpropagation, and quantization across Mamba2, attention, ReLU2, and routed experts.

Read post →

Jul 9, 2026

GGUF: The File Format That Made Local LLMs Practical

GGUF: The File Format That Made Local LLMs Practical Format deep dive GGUF is not just a container for weights. It is a single-file deployment unit that carries the model architecture, token...

Read post →

Jul 2, 2026

K-Quants Deep Dive: Q4_K, Q5_K, Q6_K, Q8_K And Mixed Dot Products

ML systems · Quantization internals This ShivasNotes deep dive is the granular companion to the broader Quantization Deep Dive in this series. The earlier post explained why quantization ma...

Read post →

Jun 20, 2026

Quantization Deep Dive: How CPU Kernels Compress Weights and Preserve Accuracy

Quantization deep dive · ML fundamentals This ShivasNotes deep dive is written for CPU silicon teams evaluating whether C-Kernel-Engine really owns its quantized inference path. The answer ...

Read post →

Jun 18, 2026

SIMD Deep Dive: How AI Kernels Use SSE, AVX, AVX-512, and VNNI

ML fundamentals · SIMD deep dive This ShivasNotes deep dive is written for CPU silicon teams evaluating kernel-level software competence. The subject is not “can the model run?” but “...

Read post →

Quantization

Why 4-Bit Quantization Is King: Understanding Q4_K, MXFP4, and NVFP4

What Numerical Parity Actually Requires: BF16, Quantization, ISA Drift And CKE X-Ray

Nemotron Kernels From Inference To Backpropagation

GGUF: The File Format That Made Local LLMs Practical

K-Quants Deep Dive: Q4_K, Q5_K, Q6_K, Q8_K And Mixed Dot Products

Quantization Deep Dive: How CPU Kernels Compress Weights and Preserve Accuracy

SIMD Deep Dive: How AI Kernels Use SSE, AVX, AVX-512, and VNNI

Need an intelligent system to work on real hardware?

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

ShivasNotes

Read

Support

Owned by Antshiv Robotics

Published with Antsand

Why 4-Bit Quantization Is King: Understanding Q4_K, MXFP4, and NVFP4

What Numerical Parity Actually Requires: BF16, Quantization, ISA Drift And CKE X-Ray

Nemotron Kernels From Inference To Backpropagation

GGUF: The File Format That Made Local LLMs Practical

K-Quants Deep Dive: Q4_K, Q5_K, Q6_K, Q8_K And Mixed Dot Products

Quantization Deep Dive: How CPU Kernels Compress Weights and Preserve Accuracy

SIMD Deep Dive: How AI Kernels Use SSE, AVX, AVX-512, and VNNI

Follow the work. Understand the machine.

How to think like an AI kernel & HPC engineer

A note when there’s something to share.

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

Owned by Antshiv Robotics

Published with Antsand