| .. |
|
all_reduce
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
hai 5 meses |
|
attention
|
9d7beaa5b9
chore: separate kv_scale into k_scale and v_scale
|
hai 4 meses |
|
backup
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
hai 9 meses |
|
cpu
|
9d7beaa5b9
chore: separate kv_scale into k_scale and v_scale
|
hai 4 meses |
|
hadamard
|
5d288aa76c
feat: add fast hadamard transformation kernels (#232)
|
hai 11 meses |
|
mamba
|
f5d52320da
Port mamba kernels to Aphrodite (#595)
|
hai 4 meses |
|
moe
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
hai 5 meses |
|
prepare_inputs
|
dd18c5042c
move prepare_inputs to the GPU (#596)
|
hai 4 meses |
|
punica
|
4f42985b5c
feat: qwen2 lora shapes
|
hai 5 meses |
|
quantization
|
ba371fbbbd
feat: AWQ marlin kernels (#603)
|
hai 4 meses |
|
sampling
|
815736fc54
feat: add cuda kernels for sampling
|
hai 4 meses |
|
activation_kernels.cu
|
c0c336aaa3
refactor: registry for processing model inputs; quick_gelu; clip model support
|
hai 5 meses |
|
cache.h
|
9d7beaa5b9
chore: separate kv_scale into k_scale and v_scale
|
hai 4 meses |
|
cache_kernels.cu
|
9d7beaa5b9
chore: separate kv_scale into k_scale and v_scale
|
hai 4 meses |
|
cuda_compat.h
|
00acf371f9
rocm: fused topk softmax
|
hai 5 meses |
|
cuda_utils.h
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
hai 5 meses |
|
cuda_utils_kernels.cu
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
hai 5 meses |
|
dispatch_utils.h
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
hai 5 meses |
|
layernorm_kernels.cu
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
hai 5 meses |
|
ops.h
|
815736fc54
feat: add cuda kernels for sampling
|
hai 4 meses |
|
pos_encoding_kernels.cu
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
hai 5 meses |
|
reduction.cuh
|
aba03b4756
feat: dynamic per-token activation quantization
|
hai 5 meses |
|
registration.h
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
hai 5 meses |
|
torch_bindings.cpp
|
815736fc54
feat: add cuda kernels for sampling
|
hai 4 meses |
AlpinDale
815736fc54
feat: add cuda kernels for sampling