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).

AlpinDale a401f8e05d feat: per-tensor token epilogue kernels (#630)		4 months ago
..
broadcast_load_epilogue_c2x.hpp	a401f8e05d feat: per-tensor token epilogue kernels (#630)	4 months ago
broadcast_load_epilogue_c3x.hpp	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
common.hpp	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
scaled_mm_c2x.cu	a401f8e05d feat: per-tensor token epilogue kernels (#630)	4 months ago
scaled_mm_c2x.cuh	a401f8e05d feat: per-tensor token epilogue kernels (#630)	4 months ago
scaled_mm_c2x_sm75_dispatch.cuh	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
scaled_mm_c2x_sm80_dispatch.cuh	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
scaled_mm_c2x_sm89_fp8_dispatch.cuh	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
scaled_mm_c2x_sm89_int8_dispatch.cuh	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
scaled_mm_c3x.cu	a401f8e05d feat: per-tensor token epilogue kernels (#630)	4 months ago
scaled_mm_entry.cu	a401f8e05d feat: per-tensor token epilogue kernels (#630)	4 months ago