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

[CI] Align multi-node nightly test paramter with corresponding tutorials document (#5756)

Browse Source 
### What this PR does / why we need it?
Align multi-node nightly test paramter with tutorials documents.

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

### How was this patch tested?
Test locally and nighly e2e multi-node test cases.

- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef

---------

Signed-off-by: leo-pony <nengjunma@outlook.com>
This commit is contained in:
Nengjun Ma
2026-01-12 09:00:31 +08:00
committed by GitHub
parent 6880c1b383
commit 297f6deb09
10 changed files with 66 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
tests/e2e/nightly/multi_node/config/DeepSeek-R1-W8A8.yaml
View File

@@ -3,11 +3,12 @@ model: "vllm-ascend/DeepSeek-R1-0528-W8A8"
num_nodes: 4
npu_per_node: 16
env_common:
HCCL_OP_EXPANSION_MODE: AIV
VLLM_USE_MODELSCOPE: true
HCCL_BUFFSIZE: 1024
SERVER_PORT: 8080
OMP_PROC_BIND: false
OMP_NUM_THREADS: 10
OMP_NUM_THREADS: 1
PYTORCH_NPU_ALLOC_CONF: expandable_segments:True
HCCL_DETERMINISTIC: True
TASK_QUEUE_ENABLE: 1
@@ -36,6 +37,7 @@ deployment:
--max-num-batched-tokens 16384
--trust-remote-code
--gpu-memory-utilization 0.9
--no-enable-prefix-caching
--speculative-config '{"num_speculative_tokens": 1, "method":"mtp"}'
--kv-transfer-config
'{"kv_connector": "MooncakeConnectorV1",
@@ -55,7 +57,7 @@ deployment:
}
}'
--additional-config
'{"enable_prefill_optimizations":true,"enable_weight_nz_layout":true}'
'{"recompute_scheduler_enable":true}'
-
server_cmd: >
@@ -74,6 +76,7 @@ deployment:
--max-num-batched-tokens 16384
--trust-remote-code
--gpu-memory-utilization 0.9
--no-enable-prefix-caching
--speculative-config '{"num_speculative_tokens": 1, "method":"mtp"}'
--kv-transfer-config
'{"kv_connector": "MooncakeConnectorV1",
@@ -93,7 +96,7 @@ deployment:
}
}'
--additional-config
'{"enable_prefill_optimizations":true,"enable_weight_nz_layout":true}'
'{"recompute_scheduler_enable":true}'
-
server_cmd: >
vllm serve vllm-ascend/DeepSeek-R1-0528-W8A8
@@ -113,7 +116,9 @@ deployment:
--max-num-batched-tokens 256
--trust-remote-code
--gpu-memory-utilization 0.9
--no-enable-prefix-caching
--speculative-config '{"num_speculative_tokens": 1, "method":"mtp"}'
--compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}'
--kv-transfer-config
'{"kv_connector": "MooncakeConnectorV1",
"kv_role": "kv_consumer",
@@ -132,7 +137,11 @@ deployment:
}
}'
--additional-config
'{"multistream_overlap_shared_expert":true}'
'{"recompute_scheduler_enable":true,
"enable_shared_expert_dp":true,
"multistream_overlap_shared_expert":true,
"finegrained_tp_config": {"lmhead_tensor_parallel_size":8}
}'
-
server_cmd: >
vllm serve vllm-ascend/DeepSeek-R1-0528-W8A8
@@ -151,7 +160,9 @@ deployment:
--max-num-batched-tokens 256
--trust-remote-code
--gpu-memory-utilization 0.9
--no-enable-prefix-caching
--speculative-config '{"num_speculative_tokens": 1, "method":"mtp"}'
--compilation-config '{"cudagraph_mode": "FULL_DECODE_ONLY"}'
--kv-transfer-config
'{"kv_connector": "MooncakeConnectorV1",
"kv_role": "kv_consumer",
@@ -170,7 +181,11 @@ deployment:
}
}'
--additional-config
'{"multistream_overlap_shared_expert":true}'
'{"recompute_scheduler_enable":true,
"enable_shared_expert_dp":true,
"multistream_overlap_shared_expert":true,
"finegrained_tp_config": {"lmhead_tensor_parallel_size":8}
}'
benchmarks:
perf:
case_type: performance