Skip to content

[ROCM] Using origin fp8 aiter kernel for Deepseek Model on MI300x #14043

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

Closed
benenzhu wants to merge 2 commits into from
Closed

[ROCM] Using origin fp8 aiter kernel for Deepseek Model on MI300x #14043

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a681b59
using origin aiter kernel for mi300x
benenzhu Nov 27, 2025
38694fc
Merge branch 'main' into fix_mi300x_deepseek
benenzhu Nov 27, 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
8 changes: 5 additions & 3 deletions python/sglang/srt/layers/quantization/fp8_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,7 @@
get_device_capability,
is_cuda,
is_flashinfer_available,
is_gfx95_supported,
is_hip,
)

Expand All @@ -45,10 +46,11 @@

if _use_aiter:
import aiter
from aiter import gemm_a8w8_blockscale, gemm_a8w8_bpreshuffle, get_hip_quant

# from aiter import gemm_a8w8_blockscale, gemm_a8w8_bpreshuffle, get_hip_quant
from aiter import gemm_a8w8_bpreshuffle, get_hip_quant
from aiter.ops.triton.gemm_a8w8_blockscale import gemm_a8w8_blockscale
if is_gfx95_supported():
from aiter import gemm_a8w8_bpreshuffle, get_hip_quant
from aiter.ops.triton.gemm_a8w8_blockscale import gemm_a8w8_blockscale

aiter_per1x128_quant = get_hip_quant(aiter.QuantType.per_1x128)

Expand Down
Loading