Skip to content
View keplerzip's full-sized avatar
3 followers · 5 following
  • 12:47 (UTC +08:00)

Block or report keplerzip

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

Popular repositories Loading

  1. llm_wiki llm_wiki Public

    2

  2. deepseek-v4-flash-a100 deepseek-v4-flash-a100 Public

    Source-only offline deployment, testing, and operations toolkit for DeepSeek-V4-Flash-0731 on 4x/8x NVIDIA A100 GPUs, pinned to a reviewed community vLLM R1 stack.

    HTML 2

  3. deepseek-v4.1-flash-a100 deepseek-v4.1-flash-a100 Public

    Offline DeepSeek-V4.1-Flash deployment for 8x A100: DSpark k5, 256K context, local APIs and measured benchmarks.

    Python 1

  4. single-dgx-spark-gb10-llm single-dgx-spark-gb10-llm Public

    Dual Qwen NVFP4 deployment, exact KV budgeting, MTP/DFlash2 acceleration, telemetry, and benchmarks for NVIDIA DGX Spark GB10

    HTML

  5. Qwen3.8-Flash-Next-NVFP4-RTX-PRO-6000-Single Qwen3.8-Flash-Next-NVFP4-RTX-PRO-6000-Single Public

    Qwen3.8 Flash-Next NVFP4 on one RTX PRO 6000: Pennyroyal SGLang, native NEXTN MTP, 256K context, C8, New API and measured benchmarks

    TypeScript

  6. deepseek-v4-flash-vision-exp-a100 deepseek-v4-flash-vision-exp-a100 Public

    Source-only A100 deployment for DeepSeek V4 Flash Vision Exp: DSpark, 256K, C32, Chat/Responses/Messages and multimodal tests.

    Python