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). @ 0f4a9ee77be8a5a4a58d8a13d66eaab4e42bcf9e

AlpinDale b03b4d4c8c fix: compute cutlass 3.x epilogues in fp32 instead of 16		7 ماه پیش
..
all_reduce	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 ماه پیش
attention	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 ماه پیش
backup	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	11 ماه پیش
cpu	271a680026 feat: inference support for PowerPC ISA	7 ماه پیش
hadamard	5d288aa76c feat: add fast hadamard transformation kernels (#232)	1 سال پیش
moe	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 ماه پیش
punica	4f42985b5c feat: qwen2 lora shapes	7 ماه پیش
quantization	b03b4d4c8c fix: compute cutlass 3.x epilogues in fp32 instead of 16	7 ماه پیش
activation_kernels.cu	c0c336aaa3 refactor: registry for processing model inputs; quick_gelu; clip model support	7 ماه پیش
cache.h	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 ماه پیش
cache_kernels.cu	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 ماه پیش
cuda_compat.h	00acf371f9 rocm: fused topk softmax	7 ماه پیش
cuda_utils.h	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 ماه پیش
cuda_utils_kernels.cu	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 ماه پیش
dispatch_utils.h	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 ماه پیش
layernorm_kernels.cu	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 ماه پیش
ops.h	c0c336aaa3 refactor: registry for processing model inputs; quick_gelu; clip model support	7 ماه پیش
pos_encoding_kernels.cu	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 ماه پیش
reduction.cuh	aba03b4756 feat: dynamic per-token activation quantization	7 ماه پیش
registration.h	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 ماه پیش
torch_bindings.cpp	c0c336aaa3 refactor: registry for processing model inputs; quick_gelu; clip model support	7 ماه پیش