Skip to content
View knowrohit's full-sized avatar
:octocat:
HBA
:octocat:
HBA
148 followers · 180 following

Achievements

Achievement: QuickdrawAchievement: StarstruckAchievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: QuickdrawAchievement: StarstruckAchievement: Pull Sharkx2Achievement: YOLO

Highlights

  • Pro

Block or report knowrohit

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. Markdown is supported. 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
knowrohit/README.md

i like to engineer systems to make them run faster or to make them run efficiently on constrained hardware.

Pinned Loading

  1. SRSWTI/knivesysl SRSWTI/knivesysl Public

    bare-cuda fp6 inference engine for qwen3.8-27b on one rtx 5090 — sm120 tensor-core kernels, 256k context, near-lossless perf too!

    Cuda

  2. SRSWTI/shooting-brake SRSWTI/shooting-brake Public

    run a 118b moe on one 5090 and two intel b70s. 88 tok/s. yes cuda and sycl both runtimes talking to each other. beating rtx pro 6000 on 120k ctx plus.

    C++

  3. SRSWTI/axe SRSWTI/axe Public

    axe - a precision agentic coder. large codebases. zero bloat. terminal-native. precise retrieval. powerful inference.

    Python 36 5

  4. SRSWTI/fasterpc SRSWTI/fasterpc Public

    rpc over websockets

    Python 11 1

  5. SRSWTI/shadows SRSWTI/shadows Public

    a fast and lightweight distributed background task processing framework with seamless scheduling.

    Python 15

  6. SRSWTI/bodega-inference-engine SRSWTI/bodega-inference-engine Public

    fastest runtime for apple silicon.

    Python 90 3