how do I run this on windows docker (WSL2) with an AMD RX 6800, I have been at this for 12+ hours

[thedig123]

SGLANG version: lmsysorg/sglang:v0.4.4.post3-rocm630 (68 GB)
WSL2 base: ubuntu noble
GPU: AMD radeon RX 6800
windows: version 11
windows amd gpu drivers: PRO 24.Q4
ubuntu (WSL2) drivers: none as I can not install it, I am not sure why, I have tried nearly everything, I have amdgpu.noretry=0, I have rocm (or at least the tools on my wsl2) It is seeing /dev/dri, but not /dev/kfd when lsing /dev/dri I get both /dev/dri/card0 and /dev/dri/renderD128

i am not sure how to fix this I have tried using deepseek to the best of my ability, I have tried to make amdgpu kernels, as I thought that was the issue, but when

#!/bin/bash

docker run -it --rm \
    --device=/dev/dri/card0 \
    --device=/dev/dri/renderD128 \
    --shm-size 32g \
    -p 30000:30000 \
    --network=host \
    --privileged \
    -v /$(wslpath -m ~/.cache/huggingface):/root/.cache/huggingface \
    --ipc=host \
    --group-add video \
    --cap-add=SYS_PTRACE \
    --security-opt seccomp=unconfined \
    --env "HF_TOKEN=*HF TOKEN*" \
    --env HSA_OVERRIDE_GFX_VERSION=11.0.0 \
    --env HIP_VISIBLE_DEVICES=0 \
    lmsysorg/sglang:v0.4.4.post3-rocm630 \
    python3 -m sglang.launch_server \
    --model deepseek-ai/DeepSeek-V3 \
    --tp 8 \
    --trust-remote-code \
    --port 30000 \
    --attention-backend flashinfer \
    --quantization fp

 it is code deepseek gave me as I don't think I can use the docker run on the site as that is for Nvidia as far as I can tell, using sglang:latest is solely using Nvidia again as far as I can tell as it complains I dont have nvidia drivers (duh, docker) I am so lost when running that bash script i get 

WARNING: Published ports are discarded when using host network mode
INFO 04-03 02:07:13 __init__.py:183] No platform detected, vLLM is running on UnspecifiedPlatform
Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "/sgl-workspace/sglang/python/sglang/launch_server.py", line 6, in <module>
    from sglang.srt.entrypoints.http_server import launch_server
  File "/sgl-workspace/sglang/python/sglang/srt/entrypoints/http_server.py", line 45, in <module>
    from sglang.srt.entrypoints.engine import _launch_subprocesses
  File "/sgl-workspace/sglang/python/sglang/srt/entrypoints/engine.py", line 40, in <module>
    from sglang.srt.managers.data_parallel_controller import (
  File "/sgl-workspace/sglang/python/sglang/srt/managers/data_parallel_controller.py", line 27, in <module>
    from sglang.srt.managers.io_struct import (
  File "/sgl-workspace/sglang/python/sglang/srt/managers/io_struct.py", line 25, in <module>
    from sglang.srt.managers.schedule_batch import BaseFinishReason
  File "/sgl-workspace/sglang/python/sglang/srt/managers/schedule_batch.py", line 43, in <module>
    from sglang.srt.configs.model_config import ModelConfig
  File "/sgl-workspace/sglang/python/sglang/srt/configs/model_config.py", line 25, in <module>
    from sglang.srt.layers.quantization import QUANTIZATION_METHODS
  File "/sgl-workspace/sglang/python/sglang/srt/layers/quantization/__init__.py", line 54, in <module>
    from sglang.srt.layers.moe.fused_moe_triton.layer import FusedMoE
  File "/sgl-workspace/sglang/python/sglang/srt/layers/moe/fused_moe_triton/__init__.py", line 4, in <module>
    import sglang.srt.layers.moe.fused_moe_triton.fused_moe  # noqa
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/sgl-workspace/sglang/python/sglang/srt/layers/moe/fused_moe_triton/fused_moe.py", line 15, in <module>
    from sglang.srt.layers.moe.topk import select_experts
  File "/sgl-workspace/sglang/python/sglang/srt/layers/moe/topk.py", line 97, in <module>
    @torch.compile(dynamic=True, backend=get_compiler_backend())
     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/__init__.py", line 2504, in fn
    return compile(
           ^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/__init__.py", line 2533, in compile
    return torch._dynamo.optimize(
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/_dynamo/eval_frame.py", line 846, in optimize
    return _optimize(rebuild_ctx, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/_dynamo/eval_frame.py", line 921, in _optimize
    backend.get_compiler_config()
  File "/usr/local/lib/python3.12/dist-packages/torch/__init__.py", line 2317, in get_compiler_config
    from torch._inductor.compile_fx import get_patched_config_dict
  File "/usr/local/lib/python3.12/dist-packages/torch/_inductor/compile_fx.py", line 97, in <module>
    from .fx_passes.joint_graph import joint_graph_passes
  File "/usr/local/lib/python3.12/dist-packages/torch/_inductor/fx_passes/joint_graph.py", line 22, in <module>
    from ..pattern_matcher import (
  File "/usr/local/lib/python3.12/dist-packages/torch/_inductor/pattern_matcher.py", line 95, in <module>
    from .lowering import fallback_node_due_to_unsupported_type
    target = driver.active.get_current_target()
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/triton/backends/amd/driver.py", line 499, in get_current_target
    device = self.get_current_device()
             ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/torch/cuda/__init__.py", line 955, in current_device
    _lazy_init()
  File "/usr/local/lib/python3.12/dist-packages/torch/cuda/__init__.py", line 320, in _lazy_init
    torch._C._cuda_init()
RuntimeError: No HIP GPUs are available
/usr/local/lib/python3.12/dist-packages/torch/cuda/__init__.py:705: UserWarning: Can't initialize amdsmi - Error code: 34
  warnings.warn(f"Can't initialize amdsmi - Error code: {e.err_code}")

please help, I have no clue to fix this I have uninstalled and reinstalled sglang, deleted ubuntu change from wsl1 to wsl2 i....dont know what to do :(