xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-16 23:27:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

format

Browse Source 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
This commit is contained in:
vllmellm 2025-11-18 12:13:46 +00:00
parent 9d94f5d4f0
commit 1c5f63343f
1 changed files with 1 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tests/compile/test_sequence_parallelism.py
View File

@ -30,7 +30,6 @@ from vllm.model_executor.layers.layernorm import RMSNorm
from vllm.model_executor.layers.quantization.utils.quant_utils import ( from vllm.model_executor.layers.quantization.utils.quant_utils import (
kFp8StaticTensorSym, kFp8StaticTensorSym,
) )
from vllm.model_executor.layers.quantization.utils.quant_utils import GroupShape
from vllm.platforms import current_platform from vllm.platforms import current_platform
from vllm.utils.system_utils import update_environment_variables from vllm.utils.system_utils import update_environment_variables
@ -119,7 +118,6 @@ class TestAllReduceRMSNormStaticQuantFP8Model(torch.nn.Module):
for i in range(3) for i in range(3)
] ]
def forward(self, hidden_states): def forward(self, hidden_states):
# avoid having graph input be an arg to a pattern directly # avoid having graph input be an arg to a pattern directly
z = torch.relu(hidden_states) z = torch.relu(hidden_states)
@ -159,9 +157,7 @@ class TestAllReduceRMSNormStaticQuantFP8Model(torch.nn.Module):
return [ return [
torch.ops._C.fused_add_rms_norm.default, torch.ops._C.fused_add_rms_norm.default,
] ]
elif any( elif any(layer.is_quant_fp8_enabled() for layer in self.fp8_linear_layers):
layer.is_quant_fp8_enabled() for layer in self.fp8_linear_layers
):
return [ return [
torch.ops._C.static_scaled_fp8_quant.default, torch.ops._C.static_scaled_fp8_quant.default,
] ]