Skip to content
View DocPang's full-sized avatar
3 followers · 0 following

Achievements

Achievement: Starstruck

Achievements

Achievement: Starstruck

Block or report DocPang

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. qwen38-k100ai-int8-optimization qwen38-k100ai-int8-optimization Public

    Qwen3.8-27B INT8/W8A8 optimization for Hygon K100AI: SGLang, TP1/TP4, DFlash2 and long-context Agent workloads

    Python 32 1

  2. qwen36-k100ai-w8a8-optimization qwen36-k100ai-w8a8-optimization Public

    Reproducible single-GPU Qwen3.6-35B-A3B W8A8 inference tuning for Hygon K100AI (gfx928) on vLLM 0.18.1.

    Python 7

  3. minimax-h3-k100ai-optimization minimax-h3-k100ai-optimization Public

    MiniMax H3 INT8 ConvRot optimization and dual-K100AI QKV/Attention inference for Hygon K100AI (gfx928)

    Python 2

  4. strata-k100ai strata-k100ai Public

    Strata for K100AI：面向海光 K100AI 的 Strata 推理优化，提供 GPU 内核适配、显存与长上下文调优，以及基于官方 DTK 镜像的轻量部署。

    Cuda 1 1

  5. qwen38-k100ai-w8a8-optimization qwen38-k100ai-w8a8-optimization Public

    Reproducible Qwen3.8-27B SmoothQuant W8A8/INT8 optimization for Hygon K100AI (R054, 262K, Prefix Cache, adaptive MTP)

    Python

  6. qwen3.8-27b-k100ai-w8a8-dflash2 qwen3.8-27b-k100ai-w8a8-dflash2 Public

    Qwen3.8-27B on Hygon K100AI (DCU gfx928), 2-card TP2: W8A8-INT8 + DFlash2 runtime-overlay candidate for the community contest - reproducible recipe, official-protocol results, honest limitations.

    Python