Skip to content

Remove mi300a #440

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 19, 2025
Merged

Remove mi300a #440

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
a6d2b59
Removing gfx940 and gfx941 targets. These have been deprecated in fav…
gshtras Feb 19, 2025
9116a19
Remove from custom kernels as well
gshtras Feb 19, 2025
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: 1 addition & 1 deletion CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@ set(PYTHON_SUPPORTED_VERSIONS "3.9" "3.10" "3.11" "3.12")
set(CUDA_SUPPORTED_ARCHS "7.0;7.2;7.5;8.0;8.6;8.7;8.9;9.0")

# Supported AMD GPU architectures.
set(HIP_SUPPORTED_ARCHS "gfx906;gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101;gfx1200;gfx1201")
set(HIP_SUPPORTED_ARCHS "gfx906;gfx908;gfx90a;gfx942;gfx1030;gfx1100;gfx1101;gfx1200;gfx1201")

#
# Supported/expected torch versions for CUDA/ROCm.
Expand Down
3 changes: 1 addition & 2 deletions csrc/quantization/fp8/amd/hip_float8_impl.h
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,6 @@
#pragma once

#if defined(__HIPCC__) && \
(defined(__gfx940__) || defined(__gfx941__) || defined(__gfx942__))
#if defined(__HIPCC__) && defined(__gfx942__)
#define __HIP__MI300__
#endif

Expand Down
3 changes: 1 addition & 2 deletions csrc/rocm/attention.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,8 +24,7 @@
#include "../attention/dtype_fp8.cuh"
#include "../quantization/fp8/amd/quant_utils.cuh"

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

Expand Down
6 changes: 2 additions & 4 deletions csrc/rocm/custom_kernels.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,13 +5,11 @@
#include <algorithm>
#include "cuda_compat.h"

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

#if defined(__HIPCC__) && \
(defined(__gfx940__) || defined(__gfx941__) || defined(__gfx942__))
#if defined(__HIPCC__) && defined(__gfx942__)
#define __HIP__MI300__
#endif

Expand Down
3 changes: 1 addition & 2 deletions vllm/attention/backends/rocm_flash_attn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,8 +25,7 @@
_PARTITION_SIZE_ROCM = 256
_GPU_ARCH = torch.cuda.get_device_properties("cuda").gcnArchName
_ON_NAVI = "gfx1" in _GPU_ARCH
_ON_MI250_MI300 = any(arch in _GPU_ARCH
for arch in ["gfx90a", "gfx940", "gfx941", "gfx942"])
_ON_MI250_MI300 = any(arch in _GPU_ARCH for arch in ["gfx90a", "gfx942"])


class ROCmFlashAttentionBackend(AttentionBackend):
Expand Down