Skip to content
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

Jump to bottom

[ROCm] Fix build problem resulted from previous commit related to FP8 kv-cache support #2790

Merged
merged 2 commits into from
Feb 7, 2024
+16 −0
Merged

[ROCm] Fix build problem resulted from previous commit related to FP8 kv-cache support #2790

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
0e7eebd
[ROCm] Fix build problem resulted from FP8 kv-cache commit
hongxiayang Feb 6, 2024
ca871a6
remove the version check to apply the patch for both ROCm 6.0 or ROCm…
hongxiayang Feb 6, 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
1 change: 1 addition & 0 deletions Dockerfile.rocm
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,6 +79,7 @@ RUN cd /app \
&& cd vllm \
&& pip install -U -r requirements-rocm.txt \
&& bash patch_xformers.rocm.sh \
&& patch /opt/rocm/include/hip/amd_detail/amd_hip_bf16.h /app/vllm/rocm_patch/rocm_bf16.patch \
&& python3 setup.py install \
&& cd ..

Expand Down
15 changes: 15 additions & 0 deletions rocm_patch/rocm_bf16.patch
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
--- amd_hip_bf16.h 2024-02-06 18:28:58.268699142 +0000
+++ amd_hip_bf16.h.new 2024-02-06 18:28:31.988647133 +0000
@@ -90,10 +90,10 @@
#include "math_fwd.h" // ocml device functions

#if defined(__HIPCC_RTC__)
-#define __HOST_DEVICE__ __device__
+#define __HOST_DEVICE__ __device__ static
#else
#include <climits>
-#define __HOST_DEVICE__ __host__ __device__
+#define __HOST_DEVICE__ __host__ __device__ static inline
#endif

// Since we are using unsigned short to represent data in bfloat16, it can be of different sizes on
Loading