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

[2/N] Upgrade nightly doc (#5534)

Browse Source 
### What this PR does / why we need it?
Follow up https://github.com/vllm-project/vllm-ascend/pull/5479, upgrade
the corresponding doc for developers

- vLLM version: v0.13.0
- vLLM main:
45c1ca1ca1

Signed-off-by: wangli <wangli858794774@gmail.com>
This commit is contained in:
Li Wang
2025-12-31 09:11:42 +08:00
committed by GitHub
parent 98798d80a0
commit 2ee17e50a1
4 changed files with 266 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/e2e/nightly/multi_node/config/DeepSeek-V3.yaml
View File

@@ -22,7 +22,7 @@ env_common:
NUMEXPR_MAX_THREADS: 128
DISAGGREGATED_PREFILL_PROXY_SCRIPT: "examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py"
# For None kubernetes deployment, list the IPs of all nodes used in order as follow
# cluster_hosts: []
# cluster_hosts: [10.0.0.103, 10.0.0.139]
disaggregated_prefill:
enabled: true
prefiller_host_index: [0]