Skip to content
View itsyashvardhan's full-sized avatar
:octocat:
:octocat:

Organizations

@GDSC-KIIT @EddieHubCommunity @MLSAKIIT @itsyashvardhan-labs @PineBrook

Block or report itsyashvardhan

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
itsyashvardhan/README.md

यशवर्धन [ jəʃ · ʋər · d̪ʱən ]

LinkedIn

Research vllmarchitect

Optimizing Vision Encoders for Edge-Deployed Visual LLMs ICCCNet 2026 | published LNNS

  • Benchmarked 8 architectures across 4 hardware platforms; TTFT ranging from 1.6ms to 98.0ms on identical hardware
  • Identified vision encoders as the 70-85% latency bottleneck in edge VLLM deployments
  • Introduced the Cache Cliff phenomenon and Sensory Bottleneck Hypothesis

Pinned Loading

  1. FLUX FLUX Public

    No setup, L7 file sharing across devices | private, cross-platform transfers.

    JavaScript 1 1

  2. Diagflo Diagflo Public

    Idea to Canvas | Translate natural language to publishable artifacts for Product Managers and Engineering Teams

    TypeScript 1