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). @ 51cfadeb29b4c2b28b5b320ddccd862cb9e3ed0a

AlpinDale 271a680026 feat: inference support for PowerPC ISA		7 bulan lalu
..
all_reduce	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 bulan lalu
attention	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 bulan lalu
backup	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	11 bulan lalu
cpu	271a680026 feat: inference support for PowerPC ISA	7 bulan lalu
hadamard	5d288aa76c feat: add fast hadamard transformation kernels (#232)	1 tahun lalu
moe	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 bulan lalu
punica	4f42985b5c feat: qwen2 lora shapes	7 bulan lalu
quantization	5b464d36ea feat: bias epilogue support for cutlass kernels	7 bulan lalu
activation_kernels.cu	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 bulan lalu
cache.h	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 bulan lalu
cache_kernels.cu	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 bulan lalu
cuda_compat.h	00acf371f9 rocm: fused topk softmax	7 bulan lalu
cuda_utils.h	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 bulan lalu
cuda_utils_kernels.cu	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 bulan lalu
dispatch_utils.h	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 bulan lalu
layernorm_kernels.cu	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 bulan lalu
ops.h	271a680026 feat: inference support for PowerPC ISA	7 bulan lalu
pos_encoding_kernels.cu	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 bulan lalu
reduction.cuh	aba03b4756 feat: dynamic per-token activation quantization	7 bulan lalu
registration.h	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 bulan lalu
torch_bindings.cpp	5b464d36ea feat: bias epilogue support for cutlass kernels	7 bulan lalu