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). @ 2ed49cdc4c343b2acee9562d9ed474f450fc9cae

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