From e2158275030fb3e64148a4ad3ad930d24b66f7ab Mon Sep 17 00:00:00 2001 From: Gahow Wang Date: Sat, 2 May 2026 08:21:27 +0800 Subject: [PATCH] Use uv auto torch backend for vllm 0.20 --- .../examples/dash0_qwen30b_a3b_community_vllm020_harness.json | 4 ++-- .../dash0_qwen30b_a3b_community_vllm020_noharness.json | 4 ++-- .../harness-early-stop-ablation-20260502.md | 4 +++- 3 files changed, 7 insertions(+), 5 deletions(-) diff --git a/configs/examples/dash0_qwen30b_a3b_community_vllm020_harness.json b/configs/examples/dash0_qwen30b_a3b_community_vllm020_harness.json index e6930f9..bd598a0 100644 --- a/configs/examples/dash0_qwen30b_a3b_community_vllm020_harness.json +++ b/configs/examples/dash0_qwen30b_a3b_community_vllm020_harness.json @@ -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", diff --git a/configs/examples/dash0_qwen30b_a3b_community_vllm020_noharness.json b/configs/examples/dash0_qwen30b_a3b_community_vllm020_noharness.json index 7084dcb..b5520aa 100644 --- a/configs/examples/dash0_qwen30b_a3b_community_vllm020_noharness.json +++ b/configs/examples/dash0_qwen30b_a3b_community_vllm020_noharness.json @@ -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", diff --git a/docs/qwen30b-community-vllm020/harness-early-stop-ablation-20260502.md b/docs/qwen30b-community-vllm020/harness-early-stop-ablation-20260502.md index 660f36e..adb7485 100644 --- a/docs/qwen30b-community-vllm020/harness-early-stop-ablation-20260502.md +++ b/docs/qwen30b-community-vllm020/harness-early-stop-ablation-20260502.md @@ -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: