OS-Copilot

/

OS-Atlas-Pro-7B

like 16

Follow

OS-Copilot 51

Traceback (most recent call last):
  File "/opt/conda/bin/text-generation-server", line 8, in <module>
    sys.exit(app())
  File "/opt/conda/lib/python3.11/site-packages/typer/main.py", line 321, in __call__
    return get_command(self)(*args, **kwargs)
  File "/opt/conda/lib/python3.11/site-packages/click/core.py", line 1157, in __call__
    return self.main(*args, **kwargs)
  File "/opt/conda/lib/python3.11/site-packages/typer/core.py", line 728, in main
    return _main(
  File "/opt/conda/lib/python3.11/site-packages/typer/core.py", line 197, in _main
    rv = self.invoke(ctx)
  File "/opt/conda/lib/python3.11/site-packages/click/core.py", line 1688, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/opt/conda/lib/python3.11/site-packages/click/core.py", line 1434, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/opt/conda/lib/python3.11/site-packages/click/core.py", line 783, in invoke
    return __callback(*args, **kwargs)
  File "/opt/conda/lib/python3.11/site-packages/typer/main.py", line 703, in wrapper
    return callback(**use_params)
  File "/opt/conda/lib/python3.11/site-packages/text_generation_server/cli.py", line 117, in serve
    server.serve(
  File "/opt/conda/lib/python3.11/site-packages/text_generation_server/server.py", line 315, in serve
    asyncio.run(
  File "/opt/conda/lib/python3.11/asyncio/runners.py", line 190, in run
    return runner.run(main)
  File "/opt/conda/lib/python3.11/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
  File "/opt/conda/lib/python3.11/asyncio/base_events.py", line 641, in run_until_complete
    self.run_forever()
  File "/opt/conda/lib/python3.11/asyncio/base_events.py", line 608, in run_forever
    self._run_once()
  File "/opt/conda/lib/python3.11/asyncio/base_events.py", line 1936, in _run_once
    handle._run()
  File "/opt/conda/lib/python3.11/asyncio/events.py", line 84, in _run
    self._context.run(self._callback, *self._args)
  File "/opt/conda/lib/python3.11/site-packages/grpc_interceptor/server.py", line 165, in invoke_intercept_method
    return await self.intercept(
> File "/opt/conda/lib/python3.11/site-packages/text_generation_server/interceptor.py", line 24, in intercept
    return await response
  File "/opt/conda/lib/python3.11/site-packages/opentelemetry/instrumentation/grpc/_aio_server.py", line 120, in _unary_interceptor
    raise error
  File "/opt/conda/lib/python3.11/site-packages/opentelemetry/instrumentation/grpc/_aio_server.py", line 111, in _unary_interceptor
    return await behavior(request_or_iterator, context)
  File "/opt/conda/lib/python3.11/site-packages/text_generation_server/server.py", line 144, in Warmup
    self.model.warmup(batch, max_input_tokens, max_total_tokens)
  File "/opt/conda/lib/python3.11/site-packages/text_generation_server/models/flash_causal_lm.py", line 1692, in warmup
    self.cuda_graph_warmup(bs, max_total_tokens, max_total_tokens)
  File "/opt/conda/lib/python3.11/site-packages/text_generation_server/models/flash_causal_lm.py", line 1496, in cuda_graph_warmup
    self.model.forward(
  File "/opt/conda/lib/python3.11/site-packages/text_generation_server/models/custom_modeling/qwen2_vl.py", line 536, in forward
    hidden_states = self.text_model(
  File "/opt/conda/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/opt/conda/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
  File "/opt/conda/lib/python3.11/site-packages/text_generation_server/models/custom_modeling/flash_qwen2_modeling.py", line 336, in forward
    hidden_states, residual = layer(
  File "/opt/conda/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/opt/conda/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
  File "/opt/conda/lib/python3.11/site-packages/text_generation_server/models/custom_modeling/flash_qwen2_modeling.py", line 257, in forward
    attn_output = self.self_attn(
  File "/opt/conda/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/opt/conda/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
  File "/opt/conda/lib/python3.11/site-packages/text_generation_server/models/custom_modeling/flash_qwen2_modeling.py", line 141, in forward
    self.rotary_emb(query, torch.select(kv, dim=1, index=0), cos, sin)
  File "/opt/conda/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/opt/conda/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
  File "/opt/conda/lib/python3.11/site-packages/text_generation_server/layers/rotary.py", line 57, in forward
    rotary_emb.apply_rotary(q1, q2, cos, sin, q1, q2, False)
RuntimeError: The size of tensor a (16) must match the size of tensor b (32) at non-singleton dimension 0"}