Pinned Loading

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

   Forked from ggml-org/llama.cpp

   HIP/ROCm fork of llama.cpp with PrismML Bonsai Q1_0 and Q1_0_G128 1-bit GPU inference, TurboQuant TQ3_0 KV cache, and gfx1030/RDNA2 hardening.

   C++ 3

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

   Forked from sgl-project/sglang

   ROCm/HIP fork of SGLang with TurboQuant tq2/tq3/tq4 KV cache, Triton and radix-cache serving, EAGLE3 speculative decoding, P-EAGLE checkpoint support, and PrismML Bonsai 1-bit GGUF compatibility on…

   Python 1

3. SpecForge SpecForge Public

   Forked from sgl-project/SpecForge

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

   Python