Sync from v0.13

requirements/cuda.txt

@@ -0,0 +1,13 @@
+# Common dependencies
+-r common.txt
+
+numba == 0.61.2 # Required for N-gram speculative decoding
+
+# Dependencies for NVIDIA GPUs
+ray[cgraph]>=2.48.0 # Ray Compiled Graph, required for pipeline parallelism in V1.
+torch==2.9.0
+torchaudio==2.9.0
+# These must be updated alongside torch
+torchvision==0.24.0 # Required for phi3v processor. See https://github.com/pytorch/vision?tab=readme-ov-file#installation for corresponding version
+# FlashInfer should be updated together with the Dockerfile
+flashinfer-python==0.5.3