Skip to content
View iggerask's full-sized avatar

Block or report iggerask

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.

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

Popular repositories Loading

  1. dspark-mlx dspark-mlx Public

    Lossless speculative decoding for Ternary-Bonsai-27B on Apple Silicon: prism-ml's DSpark drafter ported to MLX

    Python 1

  2. wint-mcp wint-mcp Public

    MCP for Wint

    TypeScript

  3. mlx-mtp mlx-mtp Public

    MTP speculative decoding for Apple Silicon (MLX) — 1.27x throughput on Qwen3.5-35B-A3B via fused MoE kernels + zero-replay rejection

    Python

  4. deepseek-v4-flash-2bit-gb10 deepseek-v4-flash-2bit-gb10 Public

    Serve DeepSeek-V4-Flash 2-bit (299B MoE) on one DGX Spark (GB10/sm_121) — stock vLLM + vq2 plugin, ~22 tok/s

    Python 1

  5. Bonsai-demo Bonsai-demo Public

    Forked from PrismML-Eng/Bonsai-demo

    Bonsai Demo

    Shell

  6. vllm vllm Public

    Forked from vllm-project/vllm

    A high-throughput and memory-efficient inference and serving engine for LLMs

    Python