Upload offline vLLM wheel archive

.gitattributes

@@ -1,35 +1 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,25 @@
+# vLLM Nightly Wheel for Qwen3.5
+
+This archive contains a Linux x86_64 vLLM nightly wheel that supports the
+`Qwen3_5ForConditionalGeneration` architecture used by `Qwen/Qwen3.5-4B`.
+
+## Install on the cluster
+
+```bash
+tar -xzf vllm-wheel-linux-x86_64.tar.gz
+python -m pip install --no-index --no-deps --force-reinstall \
+  ./vllm-0.23.1rc1.dev102+ga46abb7ae-cp38-abi3-manylinux_2_28_x86_64.whl
+python -c "import vllm; print(vllm.__version__)"
+```
+
+## Serve Qwen3.5
+
+```bash
+CUDA_VISIBLE_DEVICES=1,2 vllm serve /cm/archive/tue09/model_hub/Qwen/Qwen3.5-4B \
+  --port 8000 \
+  --served-model-name Qwen/Qwen3.5-4B \
+  --tensor-parallel-size 2 \
+  --max-model-len 8192 \
+  --reasoning-parser qwen3 \
+  --language-model-only
+```

download_repo.py

@@ -0,0 +1,11 @@
+from huggingface_hub import snapshot_download
+
+
+repo = "LeTue09/vllm-wheel"
+
+snapshot_download(
+    repo_id=repo,
+    repo_type="model",
+    local_dir=f"/cm/shared/tue09/{repo}",
+    local_dir_use_symlinks=False,
+)

install_from_archive.sh

@@ -0,0 +1,7 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+tar -xzf vllm-wheel-linux-x86_64.tar.gz
+python -m pip install --no-index --no-deps --force-reinstall \
+  ./vllm-0.23.1rc1.dev102+ga46abb7ae-cp38-abi3-manylinux_2_28_x86_64.whl
+python -c "import vllm; print(vllm.__version__)"

vllm-wheel-linux-x86_64.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ca5b8f0632d38686082a18e82efb330e46765838ac621b1f24d80a061abc767
+size 271631344