A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 7, 01:30 UTC
[Dependency] Remove default ray dependency (#36170)
Signed-off-by: yewentao256 <zhyanwentao@126.com> Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Wentao Ye committed
Mar 8, 2026 at 23:06 UTC
384425f84e314b11076289365277b1c2650ee902
3 files changed
+6
-2
docs/serving/parallelism_scaling.md
+6
@@ -68,6 +68,12 @@ vLLM uses Ray to manage the distributed execution of tasks across multiple nodes
68
69
Ray also offers high-level APIs for large-scale [offline batch inference](https://docs.ray.io/en/latest/data/working-with-llms.html) and [online serving](https://docs.ray.io/en/latest/serve/llm) that can leverage vLLM as the engine. These APIs add production-grade fault tolerance, scaling, and distributed observability to vLLM workloads.
70
71
+Ray is an optional dependency. Install it explicitly before using Ray-based execution, for example:
72
+
73
+```bash
74
+pip install "ray[cgraph]"
75
+```
76
+
77
For details, see the [Ray documentation](https://docs.ray.io/en/latest/index.html).
78
79
### Ray cluster setup with containers
requirements/cuda.txt
-1
@@ -4,7 +4,6 @@
4
numba == 0.61.2 # Required for N-gram speculative decoding
5
6
# Dependencies for NVIDIA GPUs
7
-ray[cgraph]>=2.48.0
7
torch==2.10.0
8
torchaudio==2.10.0
9
# These must be updated alongside torch
requirements/rocm.txt
-1
@@ -10,7 +10,6 @@ numba == 0.61.2 # Required for N-gram speculative decoding
10
11
# Dependencies for AMD GPUs
12
datasets
13
-ray[cgraph]>=2.48.0
13
peft
14
pytest-asyncio
15
tensorizer==2.10.1