EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[Feature] support aclgraph for model runner v2 (#7110)

Browse Source 
### What this PR does / why we need it?
This PR aims to support aclgraph for model runner v2, please see RFC
#5208. The PR contains these modifications:
- adapt to newest commit of vllm main branch.
- supply a unified interface of extra forward context for both model
runner v1 and model runner v2.
- implement graph mode for main model. 

### Does this PR introduce _any_ user-facing change?
no

### How was this patch tested?

- vLLM version: v0.16.0
- vLLM main:
4034c3d32e

---------

Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
This commit is contained in:
Ronald
2026-03-13 09:11:46 +08:00
committed by GitHub
parent 1f71da80eb
commit c980e68d40
52 changed files with 840 additions and 309 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/ut/_310p/attention/test_attention_v1_310.py
View File

@@ -74,7 +74,7 @@ class TestAscendAttentionBackendImpl310(TestBase):
@patch("torch_npu._npu_reshape_and_cache")
@patch("torch_npu._npu_flash_attention")
@patch("vllm_ascend.attention.attention_v1.get_forward_context")
@patch("vllm_ascend.ascend_forward_context.get_forward_context")
def test_forward_prefill_310(
self, mock_get_forward_context, mock_npu_npu_flash_attention, mock_npu_reshape_and_cache
):
@@ -105,7 +105,7 @@ class TestAscendAttentionBackendImpl310(TestBase):
@patch("torch_npu.npu_format_cast", return_value=torch.randn((1, 128, 16, 16), dtype=torch.float16))
@patch("torch_npu._npu_reshape_and_cache")
@patch("torch_npu._npu_paged_attention_splitfuse")
@patch("vllm_ascend.attention.attention_v1.get_forward_context")
@patch("vllm_ascend.ascend_forward_context.get_forward_context")
def test_forward_chunked_prefill_310(
self,
mock_get_forward_context,
@@ -140,7 +140,7 @@ class TestAscendAttentionBackendImpl310(TestBase):
@patch("torch_npu.npu_format_cast", return_value=torch.randn((1, 128, 16, 16), dtype=torch.float16))
@patch("torch_npu._npu_reshape_and_cache")
@patch("torch_npu._npu_paged_attention_splitfuse")
@patch("vllm_ascend.attention.attention_v1.get_forward_context")
@patch("vllm_ascend.ascend_forward_context.get_forward_context")
def test_forward_prefill_cache_hit_310(
self,
mock_get_forward_context,
@@ -175,7 +175,7 @@ class TestAscendAttentionBackendImpl310(TestBase):
@patch("vllm_ascend.attention.attention_v1.using_paged_attention")
@patch("torch_npu._npu_paged_attention")
@patch("torch_npu._npu_reshape_and_cache")
@patch("vllm_ascend.attention.attention_v1.get_forward_context")
@patch("vllm_ascend.ascend_forward_context.get_forward_context")
def test_forward_paged_attention_310(
self, mock_get_forward_context, mock_npu_reshape_and_cache, mock_paged_attention, mock_using_paged_attention
):