xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-11 00:05:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[AMD][CI/Build][Bugfix] Guarding CUDA specific functions by ifndef ROCM (#21766)

Browse Source 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
This commit is contained in:
Gregory Shtrasberg 2025-07-28 23:35:37 -04:00 committed by GitHub
parent e18f085103
commit 12a223ef9b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
csrc/quantization/compressed_tensors/int8_quant_kernels.cu
View File

@ -1,7 +1,9 @@
#include <ATen/cuda/CUDAContext.h> #include <ATen/cuda/CUDAContext.h>
#include <torch/all.h> #include <torch/all.h>
#include "../per_token_group_quant_8bit.h" #ifndef USE_ROCM
#include "../per_token_group_quant_8bit.h"
#endif
#include <cmath> #include <cmath>
@ -339,6 +341,7 @@ void dynamic_scaled_int8_quant(
}); });
} }
#ifndef USE_ROCM
void per_token_group_quant_int8(const torch::Tensor& input, void per_token_group_quant_int8(const torch::Tensor& input,
torch::Tensor& output_q, torch::Tensor& output_q,
torch::Tensor& output_s, int64_t group_size, torch::Tensor& output_s, int64_t group_size,
@ -346,3 +349,4 @@ void per_token_group_quant_int8(const torch::Tensor& input,
per_token_group_quant_8bit(input, output_q, output_s, group_size, eps, per_token_group_quant_8bit(input, output_q, output_s, group_size, eps,
int8_min, int8_max); int8_min, int8_max);
} }
#endif