[Bug] sglang:v0.4.4 crashes when starting with optimized parameters

[Hugh-yw]

Checklist

• 1. I have searched related issues but cannot get the expected help.
• 2. The bug has not been fixed in the latest version.
• 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.
• 4. If the issue you raised is not a bug but a question, please raise a discussion at https://github.com/sgl-project/sglang/discussions/new/choose Otherwise, it will be closed.
• 5. Please use English, otherwise it will be closed.

Describe the bug

Startup parameters

              cd /sgl-workspace && python3 -m sglang.launch_server
              --model-path /root/.cache/modelscope/DeepSeek-R1
              --served-model-name deepseek-r1
              --tp 16
              --dist-init-addr $LWS_LEADER_ADDRESS:20000
              --nnodes $LWS_GROUP_SIZE
              --node-rank 0
              --trust-remote-code
              --context-length 131072
              --enable-metrics
              --host 0.0.0.0
              --port 8000
              --reasoning-parser deepseek-r1
              --enable-torch-compile
              --torch-compile-max-bs 8
              --chunked-prefill-size 16384
              --enable-flashinfer-mla
              --disable-radix-cache
              --mem-fraction-static 0.9
              --speculative-algo EAGLE
              --speculative-num-steps 3
              --speculative-eagle-topk 1
              --speculative-num-draft-tokens 4
              --speculative-draft /root/.cache/modelscope/DeepSeek-R1-NextN

sglang:v0.4.4 start failed，log:

SingleProcess AUTOTUNE benchmarking takes 2.1110 seconds and 7.5909 seconds precompiling
Capturing batches (avail_mem=6.30 GB):  68%|██████▊   | 15/22 [05:24<04:39, 39.96s/it][2025-04-01 19:16:27 TP6] Scheduler hit an exception: Traceback (most recent call last):
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 265, in __init__
    self.capture()
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 349, in capture
    ) = self.capture_one_batch_size(bs, forward)
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 441, in capture_one_batch_size
    run_once()
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 434, in run_once
    logits_output = forward(input_ids, forward_batch.positions, forward_batch)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/eval_frame.py", line 465, in _fn
    return fn(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/external_utils.py", line 40, in inner
    return fn(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1333, in forward
    hidden_states = self.model(input_ids, positions, forward_batch, input_embeds)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1293, in forward
    hidden_states, residual = layer(
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1082, in forward
    return self.forward_normal(
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1104, in forward_normal
    hidden_states = self.self_attn(
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1150, in torch_dynamo_resume_in_forward_normal_at_1104
    hidden_states = self.mlp(hidden_states)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 254, in forward
    return self.forward_normal(hidden_states)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 260, in forward_normal
    shared_output = self.shared_experts(hidden_states)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 129, in forward
    gate_up, _ = self.gate_up_proj(x)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 1269, in __call__
    return self._torchdynamo_orig_callable(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 1064, in __call__
    result = self._inner_convert(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 526, in __call__
    return _compile(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 952, in _compile
    raise InternalTorchDynamoError(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 924, in _compile
    guarded_code = compile_inner(code, one_graph, hooks, transform)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 666, in compile_inner
    return _compile_inner(code, one_graph, hooks, transform)
  File "/usr/local/lib/python3.10/dist-packages/torch/_utils_internal.py", line 87, in wrapper_function
    return function(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 699, in _compile_inner
    out_code = transform_code_object(code, transform)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/bytecode_transformation.py", line 1322, in transform_code_object
    transformations(instructions, code_options)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 231, in _fn
    torch.cuda.set_rng_state(cuda_rng_state)
  File "/usr/local/lib/python3.10/dist-packages/torch/cuda/random.py", line 77, in set_rng_state
    _lazy_call(cb)
  File "/usr/local/lib/python3.10/dist-packages/torch/cuda/__init__.py", line 249, in _lazy_call
    callable()
  File "/usr/local/lib/python3.10/dist-packages/torch/cuda/random.py", line 75, in cb
    default_generator.set_state(new_state_copy)
torch._dynamo.exc.InternalTorchDynamoError: RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.



You can suppress this exception and fall back to eager by setting:
    import torch._dynamo
    torch._dynamo.config.suppress_errors = True


During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 1999, in run_scheduler_process
    scheduler = Scheduler(server_args, port_args, gpu_id, tp_rank, dp_rank)
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 249, in __init__
    self.tp_worker = TpWorkerClass(
  File "/sgl-workspace/sglang/python/sglang/srt/managers/tp_worker.py", line 74, in __init__
    self.model_runner = ModelRunner(
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 169, in __init__
    self.initialize(min_per_gpu_memory)
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 207, in initialize
    self.init_cuda_graphs()
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 931, in init_cuda_graphs
    self.cuda_graph_runner = CudaGraphRunner(self)
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 267, in __init__
    raise Exception(
Exception: Capture cuda graph failed: RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.



You can suppress this exception and fall back to eager by setting:
    import torch._dynamo
    torch._dynamo.config.suppress_errors = True

Possible solutions:
1. disable cuda graph by --disable-cuda-graph
2. set --mem-fraction-static to a smaller value (e.g., 0.8 or 0.7)
3. disable torch compile by not using --enable-torch-compile
4. set --cuda-graph-max-bs to a smaller value (e.g., 32)
Open an issue on GitHub https://github.com/sgl-project/sglang/issues/new/choose 


[2025-04-01 19:16:27] Received sigquit from a child process. It usually means the child failed.
[2025-04-01 19:16:27 TP2] Scheduler hit an exception: Traceback (most recent call last):
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 265, in __init__
    self.capture()
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 349, in capture
    ) = self.capture_one_batch_size(bs, forward)
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 441, in capture_one_batch_size
    run_once()
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 434, in run_once
    logits_output = forward(input_ids, forward_batch.positions, forward_batch)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/eval_frame.py", line 465, in _fn
    return fn(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/external_utils.py", line 40, in inner
    return fn(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1333, in forward
    hidden_states = self.model(input_ids, positions, forward_batch, input_embeds)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1293, in forward
    hidden_states, residual = layer(
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1082, in forward
    return self.forward_normal(
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1104, in forward_normal
    hidden_states = self.self_attn(
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1150, in torch_dynamo_resume_in_forward_normal_at_1104
    hidden_states = self.mlp(hidden_states)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 254, in forward
    return self.forward_normal(hidden_states)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 260, in forward_normal
    shared_output = self.shared_experts(hidden_states)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 129, in forward
    gate_up, _ = self.gate_up_proj(x)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 1269, in __call__
    return self._torchdynamo_orig_callable(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 1064, in __call__
    result = self._inner_convert(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 526, in __call__
    return _compile(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 952, in _compile
    raise InternalTorchDynamoError(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 924, in _compile
    guarded_code = compile_inner(code, one_graph, hooks, transform)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 666, in compile_inner
    return _compile_inner(code, one_graph, hooks, transform)
  File "/usr/local/lib/python3.10/dist-packages/torch/_utils_internal.py", line 87, in wrapper_function
    return function(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 699, in _compile_inner
    out_code = transform_code_object(code, transform)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/bytecode_transformation.py", line 1322, in transform_code_object
    transformations(instructions, code_options)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 231, in _fn
    torch.cuda.set_rng_state(cuda_rng_state)
  File "/usr/local/lib/python3.10/dist-packages/torch/cuda/random.py", line 77, in set_rng_state
    _lazy_call(cb)
  File "/usr/local/lib/python3.10/dist-packages/torch/cuda/__init__.py", line 249, in _lazy_call
    callable()
  File "/usr/local/lib/python3.10/dist-packages/torch/cuda/random.py", line 75, in cb
    default_generator.set_state(new_state_copy)
torch._dynamo.exc.InternalTorchDynamoError: RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.



You can suppress this exception and fall back to eager by setting:
    import torch._dynamo
    torch._dynamo.config.suppress_errors = True


During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 1999, in run_scheduler_process
    scheduler = Scheduler(server_args, port_args, gpu_id, tp_rank, dp_rank)
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 249, in __init__
    self.tp_worker = TpWorkerClass(
  File "/sgl-workspace/sglang/python/sglang/srt/managers/tp_worker.py", line 74, in __init__
    self.model_runner = ModelRunner(
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 169, in __init__
    self.initialize(min_per_gpu_memory)
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 207, in initialize
    self.init_cuda_graphs()
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 931, in init_cuda_graphs
    self.cuda_graph_runner = CudaGraphRunner(self)
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 267, in __init__
    raise Exception(
Exception: Capture cuda graph failed: RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.



You can suppress this exception and fall back to eager by setting:
    import torch._dynamo
    torch._dynamo.config.suppress_errors = True

Possible solutions:
1. disable cuda graph by --disable-cuda-graph
2. set --mem-fraction-static to a smaller value (e.g., 0.8 or 0.7)
3. disable torch compile by not using --enable-torch-compile
4. set --cuda-graph-max-bs to a smaller value (e.g., 32)
Open an issue on GitHub https://github.com/sgl-project/sglang/issues/new/choose 


[2025-04-01 19:16:27] Received sigquit from a child process. It usually means the child failed.
Capturing batches (avail_mem=6.30 GB):  68%|██████▊   | 15/22 [06:26<03:00, 25.79s/it]
[2025-04-01 19:16:27 TP5] Scheduler hit an exception: Traceback (most recent call last):
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 265, in __init__
    self.capture()
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 349, in capture
    ) = self.capture_one_batch_size(bs, forward)
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 441, in capture_one_batch_size
    run_once()
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 434, in run_once
    logits_output = forward(input_ids, forward_batch.positions, forward_batch)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/eval_frame.py", line 465, in _fn
    return fn(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/external_utils.py", line 40, in inner
    return fn(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1333, in forward
    hidden_states = self.model(input_ids, positions, forward_batch, input_embeds)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1293, in forward
    hidden_states, residual = layer(
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1082, in forward
    return self.forward_normal(
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1104, in forward_normal
    hidden_states = self.self_attn(
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1150, in torch_dynamo_resume_in_forward_normal_at_1104
    hidden_states = self.mlp(hidden_states)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 254, in forward
    return self.forward_normal(hidden_states)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 260, in forward_normal
    shared_output = self.shared_experts(hidden_states)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 129, in forward
    gate_up, _ = self.gate_up_proj(x)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 1269, in __call__
    return self._torchdynamo_orig_callable(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 1064, in __call__
    result = self._inner_convert(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 526, in __call__
    return _compile(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 952, in _compile
    raise InternalTorchDynamoError(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 924, in _compile
    guarded_code = compile_inner(code, one_graph, hooks, transform)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 666, in compile_inner
    return _compile_inner(code, one_graph, hooks, transform)
  File "/usr/local/lib/python3.10/dist-packages/torch/_utils_internal.py", line 87, in wrapper_function
    return function(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 699, in _compile_inner
    out_code = transform_code_object(code, transform)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/bytecode_transformation.py", line 1322, in transform_code_object
    transformations(instructions, code_options)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 231, in _fn
    torch.cuda.set_rng_state(cuda_rng_state)
  File "/usr/local/lib/python3.10/dist-packages/torch/cuda/random.py", line 77, in set_rng_state
    _lazy_call(cb)
  File "/usr/local/lib/python3.10/dist-packages/torch/cuda/__init__.py", line 249, in _lazy_call
    callable()
  File "/usr/local/lib/python3.10/dist-packages/torch/cuda/random.py", line 75, in cb
    default_generator.set_state(new_state_copy)
torch._dynamo.exc.InternalTorchDynamoError: RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.



You can suppress this exception and fall back to eager by setting:
    import torch._dynamo
    torch._dynamo.config.suppress_errors = True


During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 1999, in run_scheduler_process
    scheduler = Scheduler(server_args, port_args, gpu_id, tp_rank, dp_rank)
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 249, in __init__
    self.tp_worker = TpWorkerClass(
  File "/sgl-workspace/sglang/python/sglang/srt/managers/tp_worker.py", line 74, in __init__
    self.model_runner = ModelRunner(
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 169, in __init__
    self.initialize(min_per_gpu_memory)
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 207, in initialize
    self.init_cuda_graphs()
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 931, in init_cuda_graphs
    self.cuda_graph_runner = CudaGraphRunner(self)
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 267, in __init__
    raise Exception(
Exception: Capture cuda graph failed: RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.



You can suppress this exception and fall back to eager by setting:
    import torch._dynamo
    torch._dynamo.config.suppress_errors = True

Possible solutions:
1. disable cuda graph by --disable-cuda-graph
2. set --mem-fraction-static to a smaller value (e.g., 0.8 or 0.7)
3. disable torch compile by not using --enable-torch-compile
4. set --cuda-graph-max-bs to a smaller value (e.g., 32)
Open an issue on GitHub https://github.com/sgl-project/sglang/issues/new/choose 


[2025-04-01 19:16:27 TP0] Scheduler hit an exception: Traceback (most recent call last):
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 265, in __init__
    self.capture()
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 349, in capture
    ) = self.capture_one_batch_size(bs, forward)
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 441, in capture_one_batch_size
    run_once()
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 434, in run_once
    logits_output = forward(input_ids, forward_batch.positions, forward_batch)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/eval_frame.py", line 465, in _fn
    return fn(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/external_utils.py", line 40, in inner
    return fn(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1333, in forward
    hidden_states = self.model(input_ids, positions, forward_batch, input_embeds)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1293, in forward
    hidden_states, residual = layer(
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1082, in forward
    return self.forward_normal(
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1104, in forward_normal
    hidden_states = self.self_attn(
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1150, in torch_dynamo_resume_in_forward_normal_at_1104
    hidden_states = self.mlp(hidden_states)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 254, in forward
    return self.forward_normal(hidden_states)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 260, in forward_normal
    shared_output = self.shared_experts(hidden_states)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 129, in forward
    gate_up, _ = self.gate_up_proj(x)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 1269, in __call__
    return self._torchdynamo_orig_callable(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 1064, in __call__
    result = self._inner_convert(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 526, in __call__
    return _compile(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 952, in _compile
    raise InternalTorchDynamoError(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 924, in _compile
    guarded_code = compile_inner(code, one_graph, hooks, transform)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 666, in compile_inner
    return _compile_inner(code, one_graph, hooks, transform)
  File "/usr/local/lib/python3.10/dist-packages/torch/_utils_internal.py", line 87, in wrapper_function
    return function(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 699, in _compile_inner
    out_code = transform_code_object(code, transform)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/bytecode_transformation.py", line 1322, in transform_code_object
    transformations(instructions, code_options)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 231, in _fn
    torch.cuda.set_rng_state(cuda_rng_state)
  File "/usr/local/lib/python3.10/dist-packages/torch/cuda/random.py", line 77, in set_rng_state
    _lazy_call(cb)
  File "/usr/local/lib/python3.10/dist-packages/torch/cuda/__init__.py", line 249, in _lazy_call
    callable()
  File "/usr/local/lib/python3.10/dist-packages/torch/cuda/random.py", line 75, in cb
    default_generator.set_state(new_state_copy)
torch._dynamo.exc.InternalTorchDynamoError: RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.



You can suppress this exception and fall back to eager by setting:
    import torch._dynamo
    torch._dynamo.config.suppress_errors = True


During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 1999, in run_scheduler_process
    scheduler = Scheduler(server_args, port_args, gpu_id, tp_rank, dp_rank)
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 249, in __init__
    self.tp_worker = TpWorkerClass(
  File "/sgl-workspace/sglang/python/sglang/srt/managers/tp_worker.py", line 74, in __init__
    self.model_runner = ModelRunner(
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 169, in __init__
    self.initialize(min_per_gpu_memory)
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 207, in initialize
    self.init_cuda_graphs()
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 931, in init_cuda_graphs
    self.cuda_graph_runner = CudaGraphRunner(self)
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 267, in __init__
    raise Exception(
Exception: Capture cuda graph failed: RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.



You can suppress this exception and fall back to eager by setting:
    import torch._dynamo
    torch._dynamo.config.suppress_errors = True

Possible solutions:
1. disable cuda graph by --disable-cuda-graph
2. set --mem-fraction-static to a smaller value (e.g., 0.8 or 0.7)
3. disable torch compile by not using --enable-torch-compile
4. set --cuda-graph-max-bs to a smaller value (e.g., 32)
Open an issue on GitHub https://github.com/sgl-project/sglang/issues/new/choose 


[2025-04-01 19:16:27] Received sigquit from a child process. It usually means the child failed.
[2025-04-01 19:16:27] Received sigquit from a child process. It usually means the child failed.
[2025-04-01 19:16:27 TP1] Scheduler hit an exception: Traceback (most recent call last):
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 265, in __init__
    self.capture()
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 349, in capture
    ) = self.capture_one_batch_size(bs, forward)
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 441, in capture_one_batch_size
    run_once()
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 434, in run_once
    logits_output = forward(input_ids, forward_batch.positions, forward_batch)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/eval_frame.py", line 465, in _fn
    return fn(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/external_utils.py", line 40, in inner
    return fn(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1333, in forward
    hidden_states = self.model(input_ids, positions, forward_batch, input_embeds)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1293, in forward
    hidden_states, residual = layer(
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1082, in forward
    return self.forward_normal(
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1104, in forward_normal
    hidden_states = self.self_attn(
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 1150, in torch_dynamo_resume_in_forward_normal_at_1104
    hidden_states = self.mlp(hidden_states)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 254, in forward
    return self.forward_normal(hidden_states)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 260, in forward_normal
    shared_output = self.shared_experts(hidden_states)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/sgl-workspace/sglang/python/sglang/srt/models/deepseek_v2.py", line 129, in forward
    gate_up, _ = self.gate_up_proj(x)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 1269, in __call__
    return self._torchdynamo_orig_callable(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 1064, in __call__
    result = self._inner_convert(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 526, in __call__
    return _compile(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 952, in _compile
    raise InternalTorchDynamoError(
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 924, in _compile
    guarded_code = compile_inner(code, one_graph, hooks, transform)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 666, in compile_inner
    return _compile_inner(code, one_graph, hooks, transform)
  File "/usr/local/lib/python3.10/dist-packages/torch/_utils_internal.py", line 87, in wrapper_function
    return function(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 699, in _compile_inner
    out_code = transform_code_object(code, transform)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/bytecode_transformation.py", line 1322, in transform_code_object
    transformations(instructions, code_options)
  File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/convert_frame.py", line 231, in _fn
    torch.cuda.set_rng_state(cuda_rng_state)
  File "/usr/local/lib/python3.10/dist-packages/torch/cuda/random.py", line 77, in set_rng_state
    _lazy_call(cb)
  File "/usr/local/lib/python3.10/dist-packages/torch/cuda/__init__.py", line 249, in _lazy_call
    callable()
  File "/usr/local/lib/python3.10/dist-packages/torch/cuda/random.py", line 75, in cb
    default_generator.set_state(new_state_copy)
torch._dynamo.exc.InternalTorchDynamoError: RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.



You can suppress this exception and fall back to eager by setting:
    import torch._dynamo
    torch._dynamo.config.suppress_errors = True


During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 1999, in run_scheduler_process
    scheduler = Scheduler(server_args, port_args, gpu_id, tp_rank, dp_rank)
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 249, in __init__
    self.tp_worker = TpWorkerClass(
  File "/sgl-workspace/sglang/python/sglang/srt/managers/tp_worker.py", line 74, in __init__
    self.model_runner = ModelRunner(
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 169, in __init__
    self.initialize(min_per_gpu_memory)
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 207, in initialize
    self.init_cuda_graphs()
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 931, in init_cuda_graphs
    self.cuda_graph_runner = CudaGraphRunner(self)
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/cuda_graph_runner.py", line 267, in __init__
    raise Exception(
Exception: Capture cuda graph failed: RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.



You can suppress this exception and fall back to eager by setting:
    import torch._dynamo
    torch._dynamo.config.suppress_errors = True

Possible solutions:
1. disable cuda graph by --disable-cuda-graph
2. set --mem-fraction-static to a smaller value (e.g., 0.8 or 0.7)
3. disable torch compile by not using --enable-torch-compile
4. set --cuda-graph-max-bs to a smaller value (e.g., 32)
Open an issue on GitHub https://github.com/sgl-project/sglang/issues/new/choose 


[2025-04-01 19:16:27] Received sigquit from a child process. It usually means the child failed.
sglang-0:160:2282 [1] NCCL INFO Channel 0

Reproduction

              cd /sgl-workspace && python3 -m sglang.launch_server
              --model-path /root/.cache/modelscope/DeepSeek-R1
              --served-model-name deepseek-r1
              --tp 16
              --dist-init-addr $LWS_LEADER_ADDRESS:20000
              --nnodes $LWS_GROUP_SIZE
              --node-rank 0
              --trust-remote-code
              --context-length 131072
              --enable-metrics
              --host 0.0.0.0
              --port 8000
              --reasoning-parser deepseek-r1
              --enable-torch-compile
              --torch-compile-max-bs 8
              --chunked-prefill-size 16384
              --enable-flashinfer-mla
              --disable-radix-cache
              --mem-fraction-static 0.9
              --speculative-algo EAGLE
              --speculative-num-steps 3
              --speculative-eagle-topk 1
              --speculative-num-draft-tokens 4
              --speculative-draft /root/.cache/modelscope/DeepSeek-R1-NextN

export SGL_ENABLE_JIT_DEEPGEMM=1

Environment

root@sglang-0-1:/sgl-workspace# python3 -m sglang.check_env
Python: 3.10.12 (main, Feb  4 2025, 14:57:36) [GCC 11.4.0]
CUDA available: True
GPU 0,1,2,3,4,5,6,7: NVIDIA H100 80GB HBM3
GPU 0,1,2,3,4,5,6,7 Compute Capability: 9.0
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 12.4, V12.4.131
CUDA Driver Version: 560.35.03
PyTorch: 2.5.1+cu124
sglang: 0.4.4.post3
sgl_kernel: 0.0.5.post4
flashinfer: Module Not Found
triton: 3.1.0
transformers: 4.50.0
torchao: 0.9.0
numpy: 2.2.4
aiohttp: 3.11.14
fastapi: 0.115.12
hf_transfer: 0.1.9
huggingface_hub: 0.29.3
interegular: 0.3.3
modelscope: 1.24.1
orjson: 3.10.16
outlines: 0.1.11
packaging: 24.2
psutil: 7.0.0
pydantic: 2.11.1
multipart: Module Not Found
zmq: Module Not Found
uvicorn: 0.34.0
uvloop: 0.21.0
vllm: Module Not Found
xgrammar: 0.1.17
openai: 1.69.0
tiktoken: 0.9.0
anthropic: 0.49.0
litellm: 1.65.0
decord: 0.6.0
NVIDIA Topology: 
        GPU0    GPU1    GPU2    GPU3    GPU4    GPU5    GPU6    GPU7    NIC0    NIC1    NIC2    NIC3    NIC4    NIC5    CPU Affinity    NUMA Affinity  GPU NUMA ID
GPU0     X      NV18    NV18    NV18    NV18    NV18    NV18    NV18    PIX     NODE    NODE    NODE    SYS     SYS     0-47,96-143     0              N/A
GPU1    NV18     X      NV18    NV18    NV18    NV18    NV18    NV18    NODE    NODE    NODE    NODE    SYS     SYS     0-47,96-143     0              N/A
GPU2    NV18    NV18     X      NV18    NV18    NV18    NV18    NV18    NODE    PIX     NODE    NODE    SYS     SYS     0-47,96-143     0              N/A
GPU3    NV18    NV18    NV18     X      NV18    NV18    NV18    NV18    NODE    NODE    PIX     PIX     SYS     SYS     0-47,96-143     0              N/A
GPU4    NV18    NV18    NV18    NV18     X      NV18    NV18    NV18    SYS     SYS     SYS     SYS     PIX     NODE    48-95,144-191   1              N/A
GPU5    NV18    NV18    NV18    NV18    NV18     X      NV18    NV18    SYS     SYS     SYS     SYS     NODE    NODE    48-95,144-191   1              N/A
GPU6    NV18    NV18    NV18    NV18    NV18    NV18     X      NV18    SYS     SYS     SYS     SYS     NODE    PIX     48-95,144-191   1              N/A
GPU7    NV18    NV18    NV18    NV18    NV18    NV18    NV18     X      SYS     SYS     SYS     SYS     NODE    NODE    48-95,144-191   1              N/A
NIC0    PIX     NODE    NODE    NODE    SYS     SYS     SYS     SYS      X      NODE    NODE    NODE    SYS     SYS
NIC1    NODE    NODE    PIX     NODE    SYS     SYS     SYS     SYS     NODE     X      NODE    NODE    SYS     SYS
NIC2    NODE    NODE    NODE    PIX     SYS     SYS     SYS     SYS     NODE    NODE     X      PIX     SYS     SYS
NIC3    NODE    NODE    NODE    PIX     SYS     SYS     SYS     SYS     NODE    NODE    PIX      X      SYS     SYS
NIC4    SYS     SYS     SYS     SYS     PIX     NODE    NODE    NODE    SYS     SYS     SYS     SYS      X      NODE
NIC5    SYS     SYS     SYS     SYS     NODE    NODE    PIX     NODE    SYS     SYS     SYS     SYS     NODE     X 

Legend:

  X    = Self
  SYS  = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
  NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
  PHB  = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
  PXB  = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
  PIX  = Connection traversing at most a single PCIe bridge
  NV#  = Connection traversing a bonded set of # NVLinks

NIC Legend:

  NIC0: mlx5_0
  NIC1: mlx5_1
  NIC2: mlx5_2
  NIC3: mlx5_3
  NIC4: mlx5_4
  NIC5: mlx5_5

[Fridge003]

It seems to be caused by torch compile, you can try removing --enable-torch-compile and see whether this can be solved.

[zxexz]

Running into this as well. Removing --enable-torch-compile is not a solution, it's a band-aid.

[yudian0504]

#4959

This PR should have fixed the issue.

[Hugh-yw]

The test is based on #4959. The image can be repackaged and started normally. It took 46 minutes for 2x h100*8 to start. I will do a stress test to see how the performance is.

[Hugh-yw]

The test is based on #4959. The image can be repackaged and started normally. It took 46 minutes for 2x h100*8 to start. I will do a stress test to see how the performance is.

fix new docker images:
ccr.ccs.tencentyun.com/app-public/sglang:dev-c764-0402fix

[github-actions]

This issue has been automatically closed due to inactivity. Please feel free to reopen it if needed.