david/aphrodite-engine: PygmalionAI's large-scale inference engine pygmalion.chat It is designed to serve as the inference endpoint for the PygmalionAI website, and to allow serving the Pygmalion models to a large number of users with blazing fast speeds (thanks to vLLM's Paged Attention). @ 058e629f8e26c83b4bc839fac444c66734975ba5

AlpinDale 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)		преди 7 месеца
..
quant	c41462cfcd feat: exllamav2 quantization (#305)	преди 1 година
compat.cuh	c41462cfcd feat: exllamav2 quantization (#305)	преди 1 година
matrix_view.cuh	c41462cfcd feat: exllamav2 quantization (#305)	преди 1 година
q_gemm_exl2.cu	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	преди 7 месеца
q_gemm_kernel.cuh	9d81716bfd [v0.5.3] Release Candidate (#388)	преди 10 месеца
q_matrix.cu	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	преди 7 месеца
q_matrix.cuh	c41462cfcd feat: exllamav2 quantization (#305)	преди 1 година