CookieApril/enginex-ascend-910-vllm
1
0
Fork 0
forked from EngineX-Ascend/enginex-ascend-910-vllm
Code Pull Requests Activity

init v0.11.0rc0

Browse Source
This commit is contained in:
luopingyi
2025-10-14 10:38:28 +08:00
parent 67afd0ea78
commit 66dc16f966
278 changed files with 28130 additions and 11708 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/e2e/singlecard/ops/test_rotary_embedding.py
View File

@@ -182,7 +182,7 @@ def test_rotary_embedding_quant_with_leading_dim(
)
ref_query, ref_key = rope.forward_native(positions, query, key)
query, key = torch.ops._C.rotary_embedding(
query, key = torch.ops._C_ascend.rotary_embedding(
positions,
query,
key,
@@ -239,7 +239,7 @@ class ModelwithRotaryEmbedding(nn.Module):
# we simulated a simple attention layer to test if it can be seamlessly captured into aclgraph
qkv = self.qkv_proj(hidden_states)
q, k, v = qkv.chunk(3, dim=-1)
query, key = torch.ops._C.rotary_embedding(
query, key = torch.ops._C_ascend.rotary_embedding(
positions,
q,
k,
@@ -299,7 +299,7 @@ def test_capture_rotary_embedding_in_aclgraph(
# Validate if the rotary_embedding custom kernel is indeed inside the graph by
# string match
graph = str(gm.graph)
assert "_C.rotary_embedding" in graph
assert "_C_ascend.rotary_embedding" in graph
return gm
static_positions = torch.randint(0, max_position_embeddings,