Skip to content
View 0xdfi's full-sized avatar
5 followers · 10 following

Highlights

  • Pro

Block or report 0xdfi

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. GLM-5.2-R9-Adaptive-MTP-FULL-CUDA-4x-DGX-Spark GLM-5.2-R9-Adaptive-MTP-FULL-CUDA-4x-DGX-Spark Public

    GLM-5.2 on 4x DGX Spark with adaptive MTP K2/K4/K5, FULL CUDA graphs, DCP2, 520K context, and a downloadable ARM64 runtime image.

    Python 12 1

  2. GLM-5.2-1M-4x-DGX-Spark GLM-5.2-1M-4x-DGX-Spark Public

    Unpruned GLM-5.2 (744B) at 1M context on 4x DGX Spark (GB10/sm_121a) — NVFP4 compact-KV + B12X sparse-MLA + MTP-5. Tested, stable, honest measured numbers.

    Python 9

  3. glm-5.2-dgx-spark-vllm027 glm-5.2-dgx-spark-vllm027 Public

    Measured vLLM 0.27 serving recipe for GLM-5.2 on 4x NVIDIA DGX Spark GB10 (TP4) — DCP1/DCP2/DCP4 options, full speed matrix for 12 booted configs, launcher, patches, and ops runbook

    Python 6 1

  4. vibeclawcoder-local-llm vibeclawcoder-local-llm Public

    Forked from laurentenhoor/devclaw

    Multi-project dev/qa pipeline orchestration plugin for OpenClaw

    TypeScript 3

  5. GLM-5.2-Harness-O14-4x-DGX-Spark GLM-5.2-Harness-O14-4x-DGX-Spark Public

    O14 Fast — 250K total KV, READY; O14 Balanced — 500K target, TESTING / DO NOT DEPLOY — for GLM-5.2 on 4× DGX Spark.

    Python 3 3

  6. rambar rambar Public

    Swift 1 1