f60bb474f9
### What this PR does / why we need it?
Currently our workflow run time takes about 3 hours in total, which
seriously affects the developer experience, so it is urgent to have a
optimization, after this pr, It is expected that the running time of the
full CI can be shortened to 1h40min.
- Enable linux-aarch64-a2 (64GB) to replace linux-arm64-npu (32GB)
- Change TP4 ---> TP2 * 2 max-parallel
- Move DeepSeek-V2-Lite-W8A8 to single card test
### Does this PR introduce _any_ user-facing change?
No
- vLLM version: v0.10.0
- vLLM main:
a2480251ec
---------
Signed-off-by: wangli <wangli858794774@gmail.com>
11 lines
263 B
YAML
11 lines
263 B
YAML
self-hosted-runner:
|
|
# Labels of self-hosted runner in array of strings.
|
|
labels:
|
|
- linux-aarch64-a2-0
|
|
- linux-aarch64-a2-1
|
|
- linux-aarch64-a2-2
|
|
- linux-aarch64-a2-4
|
|
- linux-aarch64-a2-8
|
|
- linux-arm64-npu-static-8
|
|
- ubuntu-24.04-arm
|