Skip to content

Fix compile error when using rocm #2648

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Feb 1, 2024
Merged

Fix compile error when using rocm #2648

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e2255a0
Fix compile error when using rocm
zhaoyang-star Jan 29, 2024
1042875
fix
zhaoyang-star Jan 30, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions csrc/attention/attention_kernels.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,9 @@

#include "attention_dtypes.h"
#include "attention_utils.cuh"
#ifdef ENABLE_FP8_E5M2
#include "../quantization/fp8_e5m2_kvcache/quant_utils.cuh"
#endif

#include <algorithm>

Expand Down
7 changes: 7 additions & 0 deletions csrc/cache_kernels.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,13 +4,20 @@

#include "cuda_compat.h"
#include "dispatch_utils.h"
#ifdef ENABLE_FP8_E5M2
#include "quantization/fp8_e5m2_kvcache/quant_utils.cuh"
#endif

#include <algorithm>
#include <cassert>
#include <map>
#include <vector>

#ifdef USE_ROCM
#include <hip/hip_bf16.h>
typedef __hip_bfloat16 __nv_bfloat16;
#endif

void swap_blocks(
torch::Tensor& src,
torch::Tensor& dst,
Expand Down
1 change: 0 additions & 1 deletion csrc/quantization/fp8_e5m2_kvcache/quant_utils.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,6 @@
#include "../../attention/dtype_float16.cuh"
#include "../../attention/dtype_bfloat16.cuh"

#pragma once

namespace vllm {
#ifdef ENABLE_FP8_E5M2
Expand Down