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

[BugFix] Require kv producer for layer sharding (#8563)

Browse Source 
### What this PR does / why we need it?

This PR introduce stricter Ascend `additional_config.layer_sharding`
validation to the 0.18 release branch so it is only accepted on
PD-disaggregated P nodes with `kv_role="kv_producer"`.


### Does this PR introduce _any_ user-facing change?

No.

### How was this patch tested?

E2E test

---------

Signed-off-by: chenchuw886 <chenchuw@huawei.com>
Co-authored-by: chenchuw886 <chenchuw@huawei.com>
This commit is contained in:
Frank Chen
2026-04-23 16:06:53 +08:00
committed by GitHub
parent 4a254ba59a
commit a4ba82e138
4 changed files with 9 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tests/ut/test_platform.py
View File

@@ -689,12 +689,13 @@ class TestNPUPlatform(TestBase):
self.assertEqual(vllm_config.cache_config.block_size, 512)
def test_validate_layer_sharding_config_accepts_single_node(self):
def test_validate_layer_sharding_config_rejects_missing_kv_transfer_config(self):
vllm_config = TestNPUPlatform.mock_vllm_config()
vllm_config.additional_config = {"layer_sharding": ["q_b_proj", "o_proj"]}
vllm_config.kv_transfer_config = None
self.platform._validate_layer_sharding_config(vllm_config)
with pytest.raises(ValueError, match="layer_sharding is only supported on P nodes"):
self.platform._validate_layer_sharding_config(vllm_config)
def test_validate_layer_sharding_config_accepts_kv_producer(self):
vllm_config = TestNPUPlatform.mock_vllm_config()