vllm/csrc/dispatch_utils.h
Luka Govedič 30870b4f66
[torch.compile] Dynamic fp8 + rms_norm fusion (#10906)
Signed-off-by: luka <luka@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
2024-12-13 03:19:23 +00:00

50 lines
2.0 KiB
C

/*
* Adapted from
* https://github.com/pytorch/pytorch/blob/v2.0.1/aten/src/ATen/Dispatch.h
*/
#pragma once
#include <torch/all.h>
#define VLLM_DISPATCH_CASE_FLOATING_TYPES(...) \
AT_DISPATCH_CASE(at::ScalarType::Float, __VA_ARGS__) \
AT_DISPATCH_CASE(at::ScalarType::Half, __VA_ARGS__) \
AT_DISPATCH_CASE(at::ScalarType::BFloat16, __VA_ARGS__)
#define VLLM_DISPATCH_FLOATING_TYPES(TYPE, NAME, ...) \
AT_DISPATCH_SWITCH(TYPE, NAME, VLLM_DISPATCH_CASE_FLOATING_TYPES(__VA_ARGS__))
// TODO(luka/varun): use FP8_TYPE macro after refactoring
#ifndef USE_ROCM
#define VLLM_DISPATCH_CASE_QUANT_TYPES(...) \
AT_DISPATCH_CASE(at::ScalarType::Float8_e4m3fn, __VA_ARGS__) \
AT_DISPATCH_CASE(at::ScalarType::Char, __VA_ARGS__)
#else
#define VLLM_DISPATCH_CASE_QUANT_TYPES(...) \
AT_DISPATCH_CASE(at::ScalarType::Float8_e4m3fnuz, __VA_ARGS__) \
AT_DISPATCH_CASE(at::ScalarType::Char, __VA_ARGS__)
#endif
#define VLLM_DISPATCH_QUANT_TYPES(TYPE, NAME, ...) \
AT_DISPATCH_SWITCH(TYPE, NAME, VLLM_DISPATCH_CASE_QUANT_TYPES(__VA_ARGS__))
#define VLLM_DISPATCH_CASE_FLOATING_AND_BYTE_TYPES(...) \
AT_DISPATCH_CASE(at::ScalarType::Float, __VA_ARGS__) \
AT_DISPATCH_CASE(at::ScalarType::Half, __VA_ARGS__) \
AT_DISPATCH_CASE(at::ScalarType::BFloat16, __VA_ARGS__) \
AT_DISPATCH_CASE(at::ScalarType::Byte, __VA_ARGS__)
#define VLLM_DISPATCH_FLOATING_AND_BYTE_TYPES(TYPE, NAME, ...) \
AT_DISPATCH_SWITCH(TYPE, NAME, \
VLLM_DISPATCH_CASE_FLOATING_AND_BYTE_TYPES(__VA_ARGS__))
#define VLLM_DISPATCH_CASE_INTEGRAL_TYPES(...) \
AT_DISPATCH_CASE(at::ScalarType::Byte, __VA_ARGS__) \
AT_DISPATCH_CASE(at::ScalarType::Char, __VA_ARGS__) \
AT_DISPATCH_CASE(at::ScalarType::Short, __VA_ARGS__) \
AT_DISPATCH_CASE(at::ScalarType::Int, __VA_ARGS__) \
AT_DISPATCH_CASE(at::ScalarType::Long, __VA_ARGS__)
#define VLLM_DISPATCH_INTEGRAL_TYPES(TYPE, NAME, ...) \
AT_DISPATCH_SWITCH(TYPE, NAME, VLLM_DISPATCH_CASE_INTEGRAL_TYPES(__VA_ARGS__))