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

Add vectorized rms_norm support for Navi31 #273

Open
wants to merge 1 commit into
base: develop
Choose a base branch
from
+5 −4
Open

Add vectorized rms_norm support for Navi31 #273

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
9 changes: 5 additions & 4 deletions csrc/layernorm_kernels.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,9 +16,10 @@
#include "quantization/fp8/nvidia/quant_utils.cuh"
#endif

#if defined(__HIPCC__) && (defined(__gfx90a__) || defined(__gfx940__) || \
defined(__gfx941__) || defined(__gfx942__))
#define __HIP__MI300_MI250__
#if defined(__HIPCC__) && \
(defined(__gfx90a__) || defined(__gfx940__) || defined(__gfx941__) || \
defined(__gfx942__) || defined(__gfx1100__))
#define __HIP__MI300_MI250_Navi31__
#endif

namespace vllm {
Expand Down Expand Up @@ -61,7 +62,7 @@ struct __align__(16) vec8_t {
__device__ scalar_t sum() const { return x + y + z + w + u + v + s + t; }
};

#ifdef __HIP__MI300_MI250__
#ifdef __HIP__MI300_MI250_Navi31__

// TODO(woosuk): Further optimize this kernel.
template <typename scalar_t>
Expand Down