Skip to content

Wave backend fixes #10

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
Hardcode84 merged 2 commits into from
May 9, 2025
Merged

Wave backend fixes #10

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
3033222
fixes
Hardcode84 May 9, 2025
8cad896
arg
Hardcode84 May 9, 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
4 changes: 2 additions & 2 deletions python/sglang/srt/layers/attention/wave_backend.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
import triton
import triton.language as tl

from sglang.srt.layers.attention import AttentionBackend
from sglang.srt.layers.attention.base_attn_backend import AttentionBackend
from sglang.srt.layers.attention.utils import create_flashinfer_kv_indices_triton
from sglang.srt.layers.dp_attention import get_attention_tp_size
from sglang.srt.model_executor.forward_batch_info import ForwardBatch, ForwardMode
Expand Down Expand Up @@ -88,7 +88,7 @@ class WaveAttnBackend(AttentionBackend):
def __init__(
self,
model_runner: ModelRunner,
skip_prefill: bool,
skip_prefill: bool = False,
kv_indptr_buf: Optional[torch.Tensor] = None,
):
# Lazy import to avoid the initialization of cuda context
Expand Down
2 changes: 1 addition & 1 deletion python/sglang/srt/layers/quantization/fp8.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -860,7 +860,7 @@ def process_weights_hip_int4(self, layer: Module):
layer.w13_weight_scale1[expert_id] *= max_w13_scales[expert_id]
layer.w2_weight_scale1[expert_id] *= layer.w2_weight_scale[expert_id]

def process_weights_hip_scale_padding(self, layer: Module, padding_size: int):
def process_weights_hip_scale_padding(self, layer: Module, padding_size: int=0):
from sglang.srt.layers.moe.fused_moe_triton.fused_moe import (
padding_size, # Avoid circular import
)
Expand Down
Loading