feat(xpu): Add Intel GPU support for veRL training

[kahlun]

What does this PR do?

Adds direct Intel GPU (Pytorch xpu variant) support to verl core for end-to-end GRPO, PPO, and SFT training using FSDP/FSDP2 + vLLM rollout (colocated mode).

Validated on: Intel Arc Pro B70 (Battlemage, 2×24 GB):

Validation (2× Arc Pro B70)

Test	Result	Performance
GRPO 1-GPU	✓	172 tok/s
GRPO 2-GPU	✓	41.6 tok/s
PPO 2-GPU	✓	27.6 tok/s
SFT 2-GPU	✓	PASS

*2-GPU throughput with same 16-prompt batch (not scaled up); full throughput benefit requires larger batch size.

Model: Qwen2.5-0.5B-Instruct, dataset: GSM8K, 16 prompts/batch.

---

Changes

Distributed (verl/utils/distributed.py):

• Composite backend "cpu:gloo,xpu:xccl" for Intel GPU process group init
• all_reduce_avg(): SUM + divide workaround (oneCCL doesn't support ReduceOp.AVG)

FSDP (verl/utils/fsdp_utils.py):

• set_force_sum_reduction_for_comms(True) for FSDP2 on Intel GPU

Ray resource mapping (verl/single_controller/ray/base.py):

• Map device "xpu" → Ray resource "GPU" (Ray's IntelGPUAccelerator registers XPU under the "GPU" key, same as CUDA)

Engine registry (verl/workers/engine/fsdp/transformer_impl.py):

• Add "xpu" to @EngineRegistry.register(device=[...]) for language and value model engines

vLLM rollout (verl/workers/rollout/vllm_rollout/vllm_async_server.py):

• Force uni executor for TP=1 on Intel GPU(avoids Level Zero multi-context OOM)
• Pop ONEAPI_DEVICE_SELECTOR before vLLM's EngineCore subprocess spawns (prevents oneDNN OpenCL init crash)
• Apply Intel GPU-specific vLLM patches before engine init

vLLM patches (verl/utils/vllm/intel_gpu_patches.py, new file):

• Skip false-OOM preflight check on Intel GPU (vllm.v1.worker.utils.request_memory)
• Wrap profiling assert in GPUWorker.determine_num_available_blocks

Runtime env (verl/trainer/constants_ppo.py):

• Propagate ZE_AFFINITY_MASK to Ray workers; explicitly drop ONEAPI_DEVICE_SELECTOR

Worker (verl/single_controller/base/worker.py):

• Intel GPU device init and get_device_name() routing

Replica (verl/workers/rollout/replica.py):

• Use get_device_name() in init_colocated / init_standalone (covers Intel GPU, CUDA, NPU generically)

Docker + tests (new files):

• docker/intel_gpu/Dockerfile.intel_gpu — reproducible build (oneAPI 2025.3, compute-runtime 26.09, torch 2.11.0+xpu, vLLM 0.17.1)
• docker/intel_gpu/README.md — setup guide
• requirements-intel-gpu.txt — intel GPU-specific pip deps
• tests/special_intel_gpu/run_grpo_intel_gpu.sh — e2e GRPO (1-GPU and 2-GPU validated)
• tests/special_intel_gpu/run_ppo_intel_gpu.sh — e2e PPO smoke test
• tests/special_intel_gpu/run_sft__intel_gpu.sh — e2e SFT smoke test

Documentation (new files):

• docs/intel_gpu_tutorial/intel_gpu_build_dockerfile_page.rst — Docker build guide, software stack table, host hardware check, full env var reference
• docs/intel_gpu_tutorial/intel_gpu_quick_start.rst — environment check, feature support matrix with perf numbers, known limitations, GRPO/PPO/SFT examples

---

All tests passing with Qwen2.5-0.5B-Instruct on GSM8K.

NUM_GPUS=1 bash tests/special_intel_gpu/run_grpo_intel_gpu.sh
# timing_s/step: 51.2,  throughput: 148.2 tok/s  ✓

NUM_GPUS=2 bash tests/special_intel_gpu/run_grpo_intel_gpu.sh
# timing_s/step: 93.0,  completes without OOM     ✓

CI: Intel GPU hardware not available in GitHub Actions. Tests are in tests/special_intel_gpu/ for manual validation.

---

Checklist Before Submitting

• Read the Contribute Guide.
• Applied pre-commit checks: all hooks pass on changed files.
• Documentation added: docs/intel_gpu_tutorial/ with build guide and quick-start.
• Tests added in tests/special_intel_gpu/ covering GRPO (1-GPU, 2-GPU), PPO, SFT.
• AI assistance used (Claude). All changes reviewed and validated end-to-end on real Intel GPU hardware.
• Not duplicating any existing open PR (no existing PR covers FSDP + vLLM direct Intel GPU integration).