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

[long_seq] remove long_seq env (#4660)

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

- vLLM version: v0.12.0

---------

Signed-off-by: LookAround <lixushi@huawei.com>
Signed-off-by: ZhangMingWei716 <2894054457@qq.com>
Co-authored-by: ZhangMingWei716 <2894054457@qq.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
LookAround0301
2025-12-05 10:31:49 +08:00
committed by GitHub
parent ea54388e19
commit b32ef53b3b
16 changed files with 230 additions and 176 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
tests/ut/test_platform.py
View File

@@ -245,6 +245,10 @@ class TestNPUPlatform(TestBase):
)
vllm_config = TestNPUPlatform.mock_vllm_config()
vllm_config.parallel_config.enable_expert_parallel = False
vllm_config.parallel_config.decode_context_parallel_size = 1
vllm_config.parallel_config.prefill_context_parallel_size = 1
vllm_config.parallel_config.decode_context_parallel_size = 1
vllm_config.parallel_config.prefill_context_parallel_size = 1
vllm_config.parallel_config.tensor_parallel_size = 1
mock_init_recompute.return_value = MagicMock()
vllm_config.scheduler_config = MagicMock()
@@ -275,6 +279,8 @@ class TestNPUPlatform(TestBase):
)
vllm_config = TestNPUPlatform.mock_vllm_config()
vllm_config.model_config = None
vllm_config.parallel_config.decode_context_parallel_size = 1
vllm_config.parallel_config.prefill_context_parallel_size = 1
vllm_config.parallel_config.tensor_parallel_size = 1
mock_init_recompute.return_value = MagicMock()
vllm_config.scheduler_config = MagicMock()
@@ -300,6 +306,8 @@ class TestNPUPlatform(TestBase):
)
vllm_config = TestNPUPlatform.mock_vllm_config()
vllm_config.model_config.enforce_eager = True
vllm_config.parallel_config.decode_context_parallel_size = 1
vllm_config.parallel_config.prefill_context_parallel_size = 1
vllm_config.parallel_config.tensor_parallel_size = 1
mock_init_recompute.return_value = MagicMock()
vllm_config.scheduler_config = MagicMock()
@@ -338,6 +346,8 @@ class TestNPUPlatform(TestBase):
)
vllm_config = TestNPUPlatform.mock_vllm_config()
vllm_config.model_config.enforce_eager = False
vllm_config.parallel_config.decode_context_parallel_size = 1
vllm_config.parallel_config.prefill_context_parallel_size = 1
vllm_config.parallel_config.tensor_parallel_size = 1
mock_init_recompute.return_value = MagicMock()
vllm_config.scheduler_config = MagicMock()
@@ -409,6 +419,8 @@ class TestNPUPlatform(TestBase):
mock_init_ascend.return_value = mock_ascend_config
vllm_config = TestNPUPlatform.mock_vllm_config()
vllm_config.model_config.enforce_eager = False
vllm_config.parallel_config.decode_context_parallel_size = 1
vllm_config.parallel_config.prefill_context_parallel_size = 1
vllm_config.parallel_config.tensor_parallel_size = 1
mock_init_recompute.return_value = MagicMock()
vllm_config.scheduler_config = MagicMock()
@@ -446,6 +458,8 @@ class TestNPUPlatform(TestBase):
vllm_config = TestNPUPlatform.mock_vllm_config()
vllm_config.cache_config.block_size = None
vllm_config.cache_config.enable_prefix_caching = True
vllm_config.parallel_config.decode_context_parallel_size = 1
vllm_config.parallel_config.prefill_context_parallel_size = 1
vllm_config.parallel_config.tensor_parallel_size = 1
mock_init_recompute.return_value = MagicMock()
vllm_config.scheduler_config = MagicMock()
@@ -472,6 +486,8 @@ class TestNPUPlatform(TestBase):
)
vllm_config = TestNPUPlatform.mock_vllm_config()
vllm_config.parallel_config.worker_cls = "auto"
vllm_config.parallel_config.decode_context_parallel_size = 1
vllm_config.parallel_config.prefill_context_parallel_size = 1
vllm_config.parallel_config.tensor_parallel_size = 1
mock_init_recompute.return_value = MagicMock()
vllm_config.scheduler_config = MagicMock()
@@ -510,6 +526,8 @@ class TestNPUPlatform(TestBase):
)
vllm_config = TestNPUPlatform.mock_vllm_config()
vllm_config.compilation_config.custom_ops = []
vllm_config.parallel_config.decode_context_parallel_size = 1
vllm_config.parallel_config.prefill_context_parallel_size = 1
vllm_config.parallel_config.tensor_parallel_size = 1
mock_init_recompute.return_value = MagicMock()