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). @ cd9ed8623b5bdc0371c785cffdecad64d550526a

AlpinDale cd9ed8623b fix: cuda version check for fp8 support in the cutlass kernels		7 mesi fa
..
all_reduce	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 mesi fa
attention	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 mesi fa
backup	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	11 mesi fa
cpu	8c32e49029 feat: add avx2 cpu support	7 mesi fa
hadamard	5d288aa76c feat: add fast hadamard transformation kernels (#232)	1 anno fa
moe	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 mesi fa
punica	da6765c084 feat: lora support for commandr models	7 mesi fa
quantization	cd9ed8623b fix: cuda version check for fp8 support in the cutlass kernels	7 mesi fa
activation_kernels.cu	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 mesi fa
cache.h	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 mesi fa
cache_kernels.cu	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 mesi fa
cuda_compat.h	00acf371f9 rocm: fused topk softmax	7 mesi fa
cuda_utils.h	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 mesi fa
cuda_utils_kernels.cu	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 mesi fa
dispatch_utils.h	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 mesi fa
layernorm_kernels.cu	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 mesi fa
ops.h	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 mesi fa
pos_encoding_kernels.cu	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 mesi fa
reduction.cuh	aba03b4756 feat: dynamic per-token activation quantization	7 mesi fa
registration.h	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 mesi fa
torch_bindings.cpp	cd9ed8623b fix: cuda version check for fp8 support in the cutlass kernels	7 mesi fa