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 8, 22:45 UTC
[Dependency] Remove comments of ray in dependency files (#33351)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Wentao Ye committed
Feb 3, 2026 at 18:30 UTC
655efb3e69bb18d150a88c0d726ca2b49f22cbdd
2 files changed
+2
-2
requirements/cuda.txt
+1
-1
@@ -4,7 +4,7 @@
4
numba == 0.61.2 # Required for N-gram speculative decoding
5
6
# Dependencies for NVIDIA GPUs
7
-ray[cgraph]>=2.48.0 # Ray Compiled Graph, required for pipeline parallelism in V1.
7
+ray[cgraph]>=2.48.0
8
torch==2.9.1
9
torchaudio==2.9.1
10
# These must be updated alongside torch
requirements/rocm.txt
+1
-1
@@ -5,7 +5,7 @@ numba == 0.61.2 # Required for N-gram speculative decoding
5
6
# Dependencies for AMD GPUs
7
datasets
8
-ray[cgraph]>=2.48.0 # Ray Compiled Graph, required for pipeline parallelism in V1.
8
+ray[cgraph]>=2.48.0
9
peft
10
pytest-asyncio
11
tensorizer==2.10.1