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

4
tests/e2e/nightly/multi_node/config/models/DeepSeek-R1-W8A8-A2-torchair.yaml
View File

@@ -30,7 +30,7 @@ deployment:
--quantization ascend
--gpu-memory-utilization 0.9
--speculative-config '{"num_speculative_tokens": 1, "method":"deepseek_mtp"}'
--additional-config '{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":true,"enable_multistream_moe":true},"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
--additional-config '{"torchair_graph_config":{"enabled":true,"enable_multistream_moe":true},"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
-
server_cmd: >
@@ -51,7 +51,7 @@ deployment:
--quantization ascend
--gpu-memory-utilization 0.9
--speculative-config '{"num_speculative_tokens": 1, "method":"deepseek_mtp"}'
--additional-config '{"ascend_scheduler_config":{"enabled":false},"torchair_graph_config":{"enabled":true,"enable_multistream_moe":true},"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
--additional-config '{"torchair_graph_config":{"enabled":true,"enable_multistream_moe":true},"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
benchmarks:
acc:
case_type: accuracy