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

hotfix: add CustomOp abstraction #1027

Merged
merged 1 commit into from
Aug 11, 2024
Merged

hotfix: add CustomOp abstraction #1027

Show file tree
Hide file tree
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
6 changes: 4 additions & 2 deletions python/sglang/srt/layers/activation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,15 +13,17 @@

import torch
import torch.nn as nn
import torch.nn.functional as F
from flashinfer.activation import silu_and_mul
from vllm.model_executor.custom_op import CustomOp


class SiluAndMul(nn.Module):
class SiluAndMul(CustomOp):
def forward_native(self, x: torch.Tensor) -> torch.Tensor:
d = x.shape[-1] // 2
return F.silu(x[..., :d]) * x[..., d:]

def forward(self, x: torch.Tensor) -> torch.Tensor:
def forward_cuda(self, x: torch.Tensor) -> torch.Tensor:
d = x.shape[-1] // 2
output_shape = x.shape[:-1] + (d,)
out = torch.empty(output_shape, dtype=x.dtype, device=x.device)
Expand Down
5 changes: 3 additions & 2 deletions python/sglang/srt/layers/layernorm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,9 +18,10 @@
import torch
import torch.nn as nn
from flashinfer.norm import fused_add_rmsnorm, rmsnorm
from vllm.model_executor.custom_op import CustomOp


class RMSNorm(nn.Module):
class RMSNorm(CustomOp):
def __init__(
self,
hidden_size: int,
Expand All @@ -30,7 +31,7 @@ def __init__(
self.weight = nn.Parameter(torch.ones(hidden_size))
self.variance_epsilon = eps

def forward(
def forward_cuda(
self,
x: torch.Tensor,
residual: Optional[torch.Tensor] = None,
Expand Down
Loading