dflash repositories

Trending repositories tagged dflash, ranked by trending score. Updated daily.

  1. 1
    AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-DFlash

    Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/aeon-7/aeon-vllm-ultimate:latest container, tuned for long-context draft acceptance on DGX Spark. 6 HF variants (BF16/NVFP4/MTP/MTP-XS), docker-compose, and QuickStart.

    GitHub · Python · 500 stars · 57 forks · +27 stars in 24 hours · Trending score 2.44

  2. 2
    Tencent/AngelSlim

    Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

    GitHub · Python · 1,811 stars · 200 forks · +15 stars in 24 hours · Trending score 2.27

  3. 3
    Luce-Org/lucebox

    Lucebox inference engine for heterogeneous hardware & consumer GPUs

    GitHub · C++ · 3,024 stars · 299 forks · +7 stars in 24 hours · Trending score 1.89

  4. 4
    hec-ovi/vllm-awq4-qwen

    vLLM Qwen 3.6-27B (AWQ-INT4) + DFlash speculative decoding on AMD Strix Halo (gfx1151 iGPU, 128 GB UMA, ROCm 7.13). 24.8 t/s single-stream, vision, tool calling, 256K context, OpenAI-compatible, Docker. Matches DGX Spark FP8+DFlash+MTP at a third of the cost. No CUDA.

    GitHub · Python · 53 stars · 5 forks · +8 stars in 24 hours · Trending score 1.60

  5. 5
    inclusionAI/ASpec

    A high-throughput training framework for Speculative decoding models.

    GitHub · Python · 58 stars · 8 forks · +1 stars in 24 hours · Trending score 0.92

  6. 6
    Havensky-stack/windows-ninfer-V100X2

    面向 Windows 11 双 Tesla V100 的本地 Qwen 推理项目:原生 C++/CUDA、中文便携启动器、TP2 通信优化、实验 MTP/DFlash、OpenAI/Anthropic 兼容 API 与 TCC/WDDM 切换。基于 NInfer 上游独立维护。

    GitHub · C++ · 13 stars · 4 forks · 0 stars in 24 hours · Trending score 0.14

  7. 7
    cryptopoly/ChaosEngineAI

    Local AI workstation: chat by voice or text, transcribe, generate images and video (with sound on Apple Silicon), benchmark and serve open-weight models. MLX, llama.cpp, vLLM and MTPLX backends, DFlash/DDTree speculative decoding, TurboQuant and TriAttention cache compression.

    GitHub · Python · 26 stars · 5 forks · 0 stars in 24 hours · Trending score 0.09

  8. 8
    AEON-7/vllm-dflash

    DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding

    GitHub · Python · 53 stars · 9 forks · −1 stars in 24 hours · Trending score 0.04

  9. 9
    vukrosic/speculative-decoding-research

    Evidence-first lab for speculative decoding, DFlash/DFlash2, block diffusion, exactness, acceptance, and inference performance

    GitHub · Shell · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  10. 10
    kk-pcl/sglang-qwen38-dual-3080-patch

    Minimal SGLang patch for Qwen3.8-27B + DFlash2 on dual RTX 3080: TP-sharded Draft fc and static per-head FP8 KV.

    GitHub · Python · 18 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00

  11. 11
    joesinvestments/GLM-5.3-Flash-Uncensored-Humming-4x-DGX-Spark

    Reproducible vLLM v0.30.0 build for Blackfrost's uncensored GLM-5.3-Flash on four DGX Sparks (TP4, NVFP4 attention, DFlash2)

    GitHub · Python · 8 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00