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

[CI] drop ascend scheduler test (#4582)

Browse Source 
let' drop ascend scheduler test first to ensure all function works
without it.


- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-12-01 20:33:50 +08:00
committed by GitHub
parent 203b4e6777
commit 27b09ca9b9
28 changed files with 53 additions and 376 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/e2e/nightly/multi_node/config/models/DeepSeek-R1-W8A8.yaml
View File

@@ -49,7 +49,7 @@ deployment:
"kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
}'
--additional-config
'{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":false,"enable_multistream_shared_expert":false},"enable_prefill_optimizations":true,"enable_weight_nz_layout":true}'
'{"torchair_graph_config":{"enabled":false,"enable_multistream_shared_expert":false},"enable_prefill_optimizations":true,"enable_weight_nz_layout":true}'
-
server_cmd: >
@@ -79,7 +79,7 @@ deployment:
"kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
}'
--additional-config
'{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":false,"enable_multistream_shared_expert":false},"enable_prefill_optimizations":true,"enable_weight_nz_layout":true}'
'{"torchair_graph_config":{"enabled":false,"enable_multistream_shared_expert":false},"enable_prefill_optimizations":true,"enable_weight_nz_layout":true}'
-
server_cmd: >
vllm serve vllm-ascend/DeepSeek-R1-0528-W8A8
@@ -110,7 +110,7 @@ deployment:
"kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
}'
--additional-config
'{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":true,"enable_multistream_mla":true,"graph_batch_sizes":[28],"use_cached_graph":true,"enable_super_kernel":false},"multistream_overlap_shared_expert":true}'
'{"torchair_graph_config":{"enabled":true,"enable_multistream_mla":true,"graph_batch_sizes":[28],"use_cached_graph":true,"enable_super_kernel":false},"multistream_overlap_shared_expert":true}'
-
server_cmd: >
vllm serve vllm-ascend/DeepSeek-R1-0528-W8A8
@@ -140,7 +140,7 @@ deployment:
"kv_connector_module_path": "vllm_ascend.distributed.llmdatadist_c_mgr_connector"
}'
--additional-config
'{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":true,"enable_multistream_mla":true,"graph_batch_sizes":[28],"use_cached_graph":true,"enable_super_kernel":false},"multistream_overlap_shared_expert":true}'
'{"torchair_graph_config":{"enabled":true,"enable_multistream_mla":true,"graph_batch_sizes":[28],"use_cached_graph":true,"enable_super_kernel":false},"multistream_overlap_shared_expert":true}'
benchmarks:
perf:
case_type: performance