[AMD] [Docker] Upgrade Python 3.12 + torch 2.11 + triton 3.7 in ROCm 7.2.4 (#30984)

Co-authored-by: Chen <bingxche@amd.com>

python/pyproject_other.toml

@@ -107,6 +107,10 @@ tracing = [
 
 # HIP (Heterogeneous-computing Interface for Portability) for AMD
 # => base docker rocm/vllm-dev:20250114, not from public vllm whl
+#
+# srt_hip_rocm724 below is the torch 2.11 variant of this list and differs only
+# in its compressed-tensors and torch pins. A dependency added here has to be
+# added there too; nothing enforces that.
 srt_hip = [
   # Pin to 0.15.0: 0.16.0 needs torch>=2.10 (incompatible with ROCm torch
   # 2.9.1). An open-ended `<0.16.0` made pip backtrack into an unbuildable
@@ -118,6 +122,17 @@ srt_hip = [
   "wave-lang==3.8.2",
 ]
 
+# Kept in step with srt_hip above by hand; only the two pins below differ.
+srt_hip_rocm724 = [
+  # ROCm 7.2.4 uses torch 2.11. compressed-tensors 0.15.0 requires
+  # torch<2.11, while 0.16.0 supports torch>=2.10.
+  "compressed-tensors==0.16.0",
+  "petit_kernel==0.0.2",
+  "sglang[runtime_common]",
+  "torch==2.11.0",
+  "wave-lang==3.8.2",
+]
+
 diffusion_hip = [
   "cache-dit==1.3.0",
   "peft>=0.18.0,<0.19.0", # Pin to <0.19.0 due to torchao incompatibility
@@ -189,11 +204,13 @@ test = [
 ]
 
 all_hip = ["sglang[diffusion_hip]", "sglang[srt_hip]", "sglang[tracing]"]
+all_hip_rocm724 = ["sglang[diffusion_hip]", "sglang[srt_hip_rocm724]", "sglang[tracing]"]
 all_hpu = ["sglang[srt_hpu]"]
 all_musa = ["sglang[diffusion_musa]", "sglang[srt_musa]"]
 all_mps = ["sglang[diffusion_mps]", "sglang[srt_mps]"]
 
 dev_hip = ["sglang[all_hip]", "sglang[test]"]
+dev_hip_rocm724 = ["sglang[all_hip_rocm724]", "sglang[test]"]
 dev_hpu = ["sglang[all_hpu]", "sglang[test]"]
 dev_musa = ["sglang[all_musa]", "sglang[test]"]
 dev_mps = ["sglang[all_mps]", "sglang[test]"]