Pinned Loading

1. llama.cpp-1-bit-turbo llama.cpp-1-bit-turbo Public

   Forked from ggml-org/llama.cpp

   HIP/ROCm fork optimized for AMD RDNA2 (gfx1030) with PrismML Q1_0_G128 1-bit quant support, RotorQuant, TurboQuant, EAGLE3 and P-EAGLE speculative decoding, and full Wave32 kernel optimizations.

   C++ 8

2. sglang-1-bit-turbo sglang-1-bit-turbo Public

   Forked from sgl-project/sglang

   AMD ROCm (gfx1030) inference fork with RotorQuant/TurboQuant KV compression, PHANTOM-X zero-copy draft speculation, EAGLE3 speculative decoding, 12 RDNA2 crash fixes, and PrismML Bonsai Q1_0_G128 1…

   Python 5

3. vllm-1-bit-turbo vllm-1-bit-turbo Public

   Forked from vllm-project/vllm

   HIP/ROCm fork optimized for AMD RDNA2 (gfx1030) with EAGLE3 speculative decoding, TurboQuant KV compression, PrismML Bonsai Q1_0_G128 1-bit GGUF support, and gfx1031 compatibility enablement.

   Python 1

4. SpecForge SpecForge Public

   Forked from sgl-project/SpecForge

   Train speculative decoding models effortlessly and port them smoothly to SGLang serving.

   Python 1

5. gfxGRAPH gfxGRAPH Public

   CUDA Graph → HIP Graph translation layer for AMD gfx1030 (RDNA2). Bridges all 4 CUDA Graph parity gaps on ROCm.

   Python 1

6. ATLAS ATLAS Public

   Forked from itigges22/ATLAS

   Adaptive Test-time Learning and Autonomous Specialization

   Python 1