gahow/aituner
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Use uv auto torch backend for vllm 0.20

Browse Source
This commit is contained in:
Gahow Wang
2026-05-02 08:21:27 +08:00
parent a7c9518ef6
commit e215827503
3 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
configs/examples/dash0_qwen30b_a3b_community_vllm020_harness.json
View File

@@ -14,7 +14,7 @@
"engine": {
"engine_name": "vllm",
"engine_version": "0.20.0",
"exec_path": "/tmp/wjh/venvs/vllm-0.20.0/bin/vllm",
"exec_path": "/tmp/wjh/venvs/vllm-0.20.0-auto/bin/vllm",
"cwd": "/home/admin/cpfs/wjh/aituner/aituner",
"host": "127.0.0.1",
"port": 18230,
@@ -57,7 +57,7 @@
"allowed_data_parallel_sizes": [1, 2, 4, 8],
"allowed_expert_parallel_sizes": [1, 2, 4, 8]
},
"python_executable": "/tmp/wjh/venvs/vllm-0.20.0/bin/python"
"python_executable": "/tmp/wjh/venvs/vllm-0.20.0-auto/bin/python"
},
"trace": {
"windows_path": "/home/admin/cpfs/wjh/aituner/aituner/trace_windows/windows.json",

4
configs/examples/dash0_qwen30b_a3b_community_vllm020_noharness.json
View File

@@ -14,7 +14,7 @@
"engine": {
"engine_name": "vllm",
"engine_version": "0.20.0",
"exec_path": "/tmp/wjh/venvs/vllm-0.20.0/bin/vllm",
"exec_path": "/tmp/wjh/venvs/vllm-0.20.0-auto/bin/vllm",
"cwd": "/home/admin/cpfs/wjh/aituner/aituner",
"host": "127.0.0.1",
"port": 18231,
@@ -57,7 +57,7 @@
"allowed_data_parallel_sizes": [1, 2, 4, 8],
"allowed_expert_parallel_sizes": [1, 2, 4, 8]
},
"python_executable": "/tmp/wjh/venvs/vllm-0.20.0/bin/python"
"python_executable": "/tmp/wjh/venvs/vllm-0.20.0-auto/bin/python"
},
"trace": {
"windows_path": "/home/admin/cpfs/wjh/aituner/aituner/trace_windows/windows.json",

4
docs/qwen30b-community-vllm020/harness-early-stop-ablation-20260502.md
View File

@@ -19,7 +19,9 @@ Both specs start from the same base vLLM configuration. The base contains only s
PyPI reports `vllm==0.20.0` as the current community release checked on 2026-05-02. The dash0 runtime venv is on local rootfs rather than CPFS, because installing torch/CUDA wheels into CPFS was I/O-bound:
`/tmp/wjh/venvs/vllm-0.20.0`
`/tmp/wjh/venvs/vllm-0.20.0-auto`
The first plain `pip install vllm==0.20.0` smoke pulled `torch 2.11.0+cu130` and failed on dash0's driver (`570.133.20`, CUDA 12.9). The active install uses the vLLM-documented `uv pip install vllm==0.20.0 --torch-backend=auto` path so uv selects a CUDA backend compatible with the installed driver.
Install log: