AlpinDale ba371fbbbd feat: AWQ marlin kernels (#603) 4 ماه پیش
..
all_reduce 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 5 ماه پیش
attention 9d7beaa5b9 chore: separate kv_scale into k_scale and v_scale 4 ماه پیش
backup f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) 9 ماه پیش
cpu 9d7beaa5b9 chore: separate kv_scale into k_scale and v_scale 4 ماه پیش
hadamard 5d288aa76c feat: add fast hadamard transformation kernels (#232) 11 ماه پیش
mamba f5d52320da Port mamba kernels to Aphrodite (#595) 4 ماه پیش
moe 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 5 ماه پیش
prepare_inputs dd18c5042c move prepare_inputs to the GPU (#596) 4 ماه پیش
punica 4f42985b5c feat: qwen2 lora shapes 5 ماه پیش
quantization ba371fbbbd feat: AWQ marlin kernels (#603) 4 ماه پیش
activation_kernels.cu c0c336aaa3 refactor: registry for processing model inputs; quick_gelu; clip model support 5 ماه پیش
cache.h 9d7beaa5b9 chore: separate kv_scale into k_scale and v_scale 4 ماه پیش
cache_kernels.cu 9d7beaa5b9 chore: separate kv_scale into k_scale and v_scale 4 ماه پیش
cuda_compat.h 00acf371f9 rocm: fused topk softmax 5 ماه پیش
cuda_utils.h 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 5 ماه پیش
cuda_utils_kernels.cu 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 5 ماه پیش
dispatch_utils.h 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 5 ماه پیش
layernorm_kernels.cu 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 5 ماه پیش
ops.h dd18c5042c move prepare_inputs to the GPU (#596) 4 ماه پیش
pos_encoding_kernels.cu 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 5 ماه پیش
reduction.cuh aba03b4756 feat: dynamic per-token activation quantization 5 ماه پیش
registration.h 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569) 5 ماه پیش
torch_bindings.cpp ba371fbbbd feat: AWQ marlin kernels (#603) 4 ماه پیش