8000 jnros (John Rose) · GitHub
[go: up one dir, main page]

Skip to content
View jnros's full-sized avatar

Block or report jnros

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
jnros/README.md

John Rose

Systems engineer - GPU inference systems, kernel/virtualization (ex-IBM Linux)
Focus: Inference, memory management, accelerated compute, quantization
Notes and consulting: lineargp.com

Selected Work

  • 2026-10 Kern 808F el Bypass over PCIe: Doorbells & DMA . analysis . repo
  • 2026-10 OpenBMC and Redfish on GB200 . analysis
  • 2026-08 SACC: Synthetic PCIe Accelerator . analysis . repo
  • 2026-07 KV Wire: RDMA over RoCE for Disaggregated Inference . analysis . repo
  • 2026-07 GPU Passthrough: IOMMU, VFIO, and Thermal Debug . analysis . repo
  • 2026-06 DiffusionBlocks AR: first language-model port, block-wise training, GPU decoupling . repo
  • 2026-05 Roofline & Ridge Point: GPU and inference optimization . repo
  • 2026-05 KV Mix: asymmetric K/V quantization, outlier-driven mixed precision . repo
  • 2026-04 Deepseek V4: system design & implications . analysis
  • 2026-04 Rootless Agent Sandbox: kernel primitives composition (ns, Landlock, seccomp) . repo
  • 2026-03 KV Compression (TurboQuant): memory + demand implications . analysis
  • 2026-03 Paged Attention: KV cache as virtual memory (CUDA) . repo
  • 2026-02 Decode Attention: Multi-Query, Multi-head, Group Query . repo
  • 2026-01 Kimi K2.5: methods + systems impact . analysis
  • 2026-01 FP64 on Blackwell INT8 (Ozaki): POC . analysis . repo
  • 2026-01 KV Offload (Engram): system design . analysis

Linux Kernel: Author of rpadlpar (mainline PCI Hotplug) and librtas (POWER userspace).

Also: quant-sampler (sampling in C, stable softmax, bit-packing) . rand-bitwise (uniform u32 RNG using Lemire's algorithm)

Background: 7 years Linux kernel at IBM. 15 years industry. Now building low-level systems/GPU/inference.

Contact: john@lineargp.com | LinkedIn

Pinned Loading

  1. cuda-attn-ref cuda-attn-ref Public

    Paged Attention: virtual memory for KV Cache in CUDA

    Cuda 2

  2. inf-bench inf-bench Public

    GPU microbenchmark: KV-cache attention (MHA, MQA, GQA) across sequence lengths

    Python

  3. kvm-experiments kvm-experiments Public

    KVM / QEMU Experiments

    Shell

  4. quant-sampler quant-sampler Public

    Quantized sampler + bit-packing demo in C

    C

  5. rand-bitwise rand-bitwise Public

    Uniform random number generator - fast range algorithm

    C

  6. CUDA-prog CUDA-prog Public

    CUDA for GPU concurrency on vector math

    Cuda

0