Random crashes with unclear cause. The log of the crash is shown below, this is with disable frontend multiprocessing and disable async output proc.
INFO: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 21.8 tokens/s, Running: 6 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 35.1%, CPU KV cache usage: 0.0%.
INFO: Prefix cache hit rate: GPU: 41.65%, CPU: 0.00%
INFO: 192.168.20.72:50892 - "GET /health HTTP/1.1" 200 OK
INFO: 192.168.20.72:50902 - "GET /health HTTP/1.1" 200 OK
INFO: 192.168.20.72:50912 - "GET /health HTTP/1.1" 200 OK
INFO: 192.168.20.72:50918 - "GET /health HTTP/1.1" 200 OK
INFO: 192.168.20.72:50918 - "GET /health HTTP/1.1" 200 OK
ERROR: Engine background task failed
Exception in callback functools.partial(<function _log_task_completion at 0x787abe3eb420>, error_callback=<bound method AsyncAphrodite._error_callback of <aphrodite.engine.async_aphrodite.AsyncAphrodite object at 0x787ab95bc210>>)
handle: <Handle functools.partial(<function _log_task_completion at 0x787abe3eb420>, error_callback=<bound method AsyncAphrodite._error_callback of <aphrodite.engine.async_aphrodite.AsyncAphrodite object at 0x787ab95bc210>>)>
Traceback (most recent call last):
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 54, in _log_task_completion
return_value = task.result()
^^^^^^^^^^^^^
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 809, in run_engine_loop
result = task.result()
^^^^^^^^^^^^^
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 735, in engine_step
request_outputs = await self.engine.step_async(virtual_engine)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 388, in step_async
self._process_model_outputs(ctx=ctx)
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/aphrodite_engine.py", line 1008, in _process_model_outputs
self.output_processor.process_outputs(
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/output_processor/single_step.py", line 91, in process_outputs
return self._process_sequence_group_outputs(sequence_group, outputs[0],
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/output_processor/single_step.py", line 204, in _process_sequence_group_outputs
scheduler.fork_seq(parent, seq)
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/scheduler.py", line 1333, in fork_seq
self.block_manager.fork(parent_seq, child_seq)
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block_manager_v2.py", line 327, in fork
self.block_tables[child_seq.seq_id] = src_block_table.fork()
^^^^^^^^^^^^^^^^^^^^^^
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/block_table.py", line 208, in fork
forked_blocks = self._allocator.fork(self._blocks[-1])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/cpu_gpu_block_allocator.py", line 206, in fork
return allocator.fork(last_block)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/prefix_caching_block.py", line 368, in fork
source_blocks = get_all_blocks_recursively(last_block)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 355, in get_all_blocks_recursively
recurse(last_block, all_blocks)
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 351, in recurse
recurse(block.prev_block, lst)
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 351, in recurse
recurse(block.prev_block, lst)
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 351, in recurse
recurse(block.prev_block, lst)
[Previous line repeated 977 more times]
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 350, in recurse
if block.prev_block is not None:
^^^^^^^^^^^^^^^^
RecursionError: maximum recursion depth exceeded
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "uvloop/cbhandles.pyx", line 63, in uvloop.loop.Handle._run
File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 66, in _log_task_completion
raise AsyncEngineDeadError(
aphrodite.engine.async_aphrodite.AsyncEngineDeadError: Task finished unexpectedly. This should never happen! Please open an issue on Github. See stack trace above for the actual cause.
ERROR: AsyncAphrodite has failed, terminating server process
INFO: 192.168.20.72:58230 - "POST /v1/completions HTTP/1.1" 500 Internal Server Error
ERROR: AsyncAphrodite has failed, terminating server process
INFO: 192.168.20.72:45800 - "POST /v1/completions HTTP/1.1" 500 Internal Server Error
ERROR: Exception in ASGI application
Traceback (most recent call last):
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 268, in __call__
await wrap(partial(self.listen_for_disconnect, receive))
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 264, in wrap
await func()
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 233, in listen_for_disconnect
message = await receive()
^^^^^^^^^^^^^^^
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/uvicorn/protocols/http/httptools_impl.py", line 563, in receive
await self.message_event.wait()
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/asyncio/locks.py", line 213, in wait
await fut
asyncio.exceptions.CancelledError: Cancelled by cancel scope 787b4c84bdd0
During handling of the above exception, another exception occurred:
+ Exception Group Traceback (most recent call last):
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/uvicorn/protocols/http/httptools_impl.py", line 409, in run_asgi
| result = await app( # type: ignore[func-returns-value]
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
| return await self.app(scope, receive, send)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/fastapi/applications.py", line 1054, in __call__
| await super().__call__(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/applications.py", line 112, in __call__
| await self.middleware_stack(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/middleware/errors.py", line 187, in __call__
| raise exc
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/middleware/errors.py", line 165, in __call__
| await self.app(scope, receive, _send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/middleware/cors.py", line 85, in __call__
| await self.app(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/middleware/exceptions.py", line 62, in __call__
| await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
| raise exc
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
| await app(scope, receive, sender)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 715, in __call__
| await self.middleware_stack(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 735, in app
| await route.handle(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 288, in handle
| await self.app(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 76, in app
| await wrap_app_handling_exceptions(app, request)(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
| raise exc
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
| await app(scope, receive, sender)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 74, in app
| await response(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 261, in __call__
| async with anyio.create_task_group() as task_group:
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 767, in __aexit__
| raise BaseExceptionGroup(
| ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception)
+-+---------------- 1 ----------------
| Traceback (most recent call last):
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 264, in wrap
| await func()
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 245, in stream_response
| async for chunk in self.body_iterator:
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/endpoints/openai/serving_chat.py", line 319, in chat_completion_stream_generator
| async for res in result_generator:
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/common/utils.py", line 466, in iterate_with_cancellation
| item = await awaits[0]
| ^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 54, in _log_task_completion
| return_value = task.result()
| ^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 809, in run_engine_loop
| result = task.result()
| ^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 735, in engine_step
| request_outputs = await self.engine.step_async(virtual_engine)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 388, in step_async
| self._process_model_outputs(ctx=ctx)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/aphrodite_engine.py", line 1008, in _process_model_outputs
| self.output_processor.process_outputs(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/output_processor/single_step.py", line 91, in process_outputs
| return self._process_sequence_group_outputs(sequence_group, outputs[0],
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/output_processor/single_step.py", line 204, in _process_sequence_group_outputs
| scheduler.fork_seq(parent, seq)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/scheduler.py", line 1333, in fork_seq
| self.block_manager.fork(parent_seq, child_seq)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block_manager_v2.py", line 327, in fork
| self.block_tables[child_seq.seq_id] = src_block_table.fork()
| ^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/block_table.py", line 208, in fork
| forked_blocks = self._allocator.fork(self._blocks[-1])
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/cpu_gpu_block_allocator.py", line 206, in fork
| return allocator.fork(last_block)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/prefix_caching_block.py", line 368, in fork
| source_blocks = get_all_blocks_recursively(last_block)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 355, in get_all_blocks_recursively
| recurse(last_block, all_blocks)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 351, in recurse
| recurse(block.prev_block, lst)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 351, in recurse
| recurse(block.prev_block, lst)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 351, in recurse
| recurse(block.prev_block, lst)
| [Previous line repeated 977 more times]
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 350, in recurse
| if block.prev_block is not None:
| ^^^^^^^^^^^^^^^^
| RecursionError: maximum recursion depth exceeded
+------------------------------------
ERROR: Exception in ASGI application
Traceback (most recent call last):
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 268, in __call__
await wrap(partial(self.listen_for_disconnect, receive))
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 264, in wrap
await func()
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 233, in listen_for_disconnect
message = await receive()
^^^^^^^^^^^^^^^
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/uvicorn/protocols/http/httptools_impl.py", line 563, in receive
await self.message_event.wait()
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/asyncio/locks.py", line 213, in wait
await fut
asyncio.exceptions.CancelledError: Cancelled by cancel scope 787b4d29b750
During handling of the above exception, another exception occurred:
+ Exception Group Traceback (most recent call last):
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/uvicorn/protocols/http/httptools_impl.py", line 409, in run_asgi
| result = await app( # type: ignore[func-returns-value]
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
| return await self.app(scope, receive, send)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/fastapi/applications.py", line 1054, in __call__
| await super().__call__(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/applications.py", line 112, in __call__
| await self.middleware_stack(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/middleware/errors.py", line 187, in __call__
| raise exc
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/middleware/errors.py", line 165, in __call__
| await self.app(scope, receive, _send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/middleware/cors.py", line 85, in __call__
| await self.app(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/middleware/exceptions.py", line 62, in __call__
| await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
| raise exc
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
| await app(scope, receive, sender)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 715, in __call__
| await self.middleware_stack(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 735, in app
| await route.handle(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 288, in handle
| await self.app(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 76, in app
| await wrap_app_handling_exceptions(app, request)(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
| raise exc
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
| await app(scope, receive, sender)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 74, in app
| await response(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 261, in __call__
| async with anyio.create_task_group() as task_group:
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 767, in __aexit__
| raise BaseExceptionGroup(
| ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception)
+-+---------------- 1 ----------------
| Traceback (most recent call last):
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 264, in wrap
| await func()
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 245, in stream_response
| async for chunk in self.body_iterator:
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/endpoints/openai/serving_chat.py", line 319, in chat_completion_stream_generator
| async for res in result_generator:
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/common/utils.py", line 466, in iterate_with_cancellation
| item = await awaits[0]
| ^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 54, in _log_task_completion
| return_value = task.result()
| ^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 809, in run_engine_loop
| result = task.result()
| ^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 735, in engine_step
| request_outputs = await self.engine.step_async(virtual_engine)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 388, in step_async
| self._process_model_outputs(ctx=ctx)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/aphrodite_engine.py", line 1008, in _process_model_outputs
| self.output_processor.process_outputs(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/output_processor/single_step.py", line 91, in process_outputs
| return self._process_sequence_group_outputs(sequence_group, outputs[0],
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/output_processor/single_step.py", line 204, in _process_sequence_group_outputs
| scheduler.fork_seq(parent, seq)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/scheduler.py", line 1333, in fork_seq
| self.block_manager.fork(parent_seq, child_seq)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block_manager_v2.py", line 327, in fork
| self.block_tables[child_seq.seq_id] = src_block_table.fork()
| ^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/block_table.py", line 208, in fork
| forked_blocks = self._allocator.fork(self._blocks[-1])
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/cpu_gpu_block_allocator.py", line 206, in fork
| return allocator.fork(last_block)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/prefix_caching_block.py", line 368, in fork
| source_blocks = get_all_blocks_recursively(last_block)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 355, in get_all_blocks_recursively
| recurse(last_block, all_blocks)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 351, in recurse
| recurse(block.prev_block, lst)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 351, in recurse
| recurse(block.prev_block, lst)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 351, in recurse
| recurse(block.prev_block, lst)
| [Previous line repeated 977 more times]
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 350, in recurse
| if block.prev_block is not None:
| ^^^^^^^^^^^^^^^^
| RecursionError: maximum recursion depth exceeded
+------------------------------------
ERROR: Exception in ASGI application
Traceback (most recent call last):
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 268, in __call__
await wrap(partial(self.listen_for_disconnect, receive))
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 264, in wrap
await func()
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 233, in listen_for_disconnect
message = await receive()
^^^^^^^^^^^^^^^
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/uvicorn/protocols/http/httptools_impl.py", line 563, in receive
await self.message_event.wait()
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/asyncio/locks.py", line 213, in wait
await fut
asyncio.exceptions.CancelledError: Cancelled by cancel scope 787b4e1c0790
During handling of the above exception, another exception occurred:
+ Exception Group Traceback (most recent call last):
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/uvicorn/protocols/http/httptools_impl.py", line 409, in run_asgi
| result = await app( # type: ignore[func-returns-value]
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
| return await self.app(scope, receive, send)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/fastapi/applications.py", line 1054, in __call__
| await super().__call__(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/applications.py", line 112, in __call__
| await self.middleware_stack(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/middleware/errors.py", line 187, in __call__
| raise exc
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/middleware/errors.py", line 165, in __call__
| await self.app(scope, receive, _send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/middleware/cors.py", line 85, in __call__
| await self.app(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/middleware/exceptions.py", line 62, in __call__
| await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
| raise exc
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
| await app(scope, receive, sender)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 715, in __call__
| await self.middleware_stack(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 735, in app
| await route.handle(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 288, in handle
| await self.app(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 76, in app
| await wrap_app_handling_exceptions(app, request)(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
| raise exc
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
| await app(scope, receive, sender)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 74, in app
| await response(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 261, in __call__
| async with anyio.create_task_group() as task_group:
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 767, in __aexit__
| raise BaseExceptionGroup(
| ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception)
+-+---------------- 1 ----------------
| Traceback (most recent call last):
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 264, in wrap
| await func()
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 245, in stream_response
| async for chunk in self.body_iterator:
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/endpoints/openai/serving_chat.py", line 319, in chat_completion_stream_generator
| async for res in result_generator:
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/common/utils.py", line 466, in iterate_with_cancellation
| item = await awaits[0]
| ^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 54, in _log_task_completion
| return_value = task.result()
| ^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 809, in run_engine_loop
| result = task.result()
| ^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 735, in engine_step
| request_outputs = await self.engine.step_async(virtual_engine)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 388, in step_async
| self._process_model_outputs(ctx=ctx)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/aphrodite_engine.py", line 1008, in _process_model_outputs
| self.output_processor.process_outputs(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/output_processor/single_step.py", line 91, in process_outputs
| return self._process_sequence_group_outputs(sequence_group, outputs[0],
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/output_processor/single_step.py", line 204, in _process_sequence_group_outputs
| scheduler.fork_seq(parent, seq)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/scheduler.py", line 1333, in fork_seq
| self.block_manager.fork(parent_seq, child_seq)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block_manager_v2.py", line 327, in fork
| self.block_tables[child_seq.seq_id] = src_block_table.fork()
| ^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/block_table.py", line 208, in fork
| forked_blocks = self._allocator.fork(self._blocks[-1])
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/cpu_gpu_block_allocator.py", line 206, in fork
| return allocator.fork(last_block)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/prefix_caching_block.py", line 368, in fork
| source_blocks = get_all_blocks_recursively(last_block)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 355, in get_all_blocks_recursively
| recurse(last_block, all_blocks)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 351, in recurse
| recurse(block.prev_block, lst)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 351, in recurse
| recurse(block.prev_block, lst)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 351, in recurse
| recurse(block.prev_block, lst)
| [Previous line repeated 977 more times]
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 350, in recurse
| if block.prev_block is not None:
| ^^^^^^^^^^^^^^^^
| RecursionError: maximum recursion depth exceeded
+------------------------------------
ERROR: Exception in ASGI application
Traceback (most recent call last):
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 268, in __call__
await wrap(partial(self.listen_for_disconnect, receive))
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 264, in wrap
await func()
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 233, in listen_for_disconnect
message = await receive()
^^^^^^^^^^^^^^^
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/uvicorn/protocols/http/httptools_impl.py", line 563, in receive
await self.message_event.wait()
File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/asyncio/locks.py", line 213, in wait
await fut
asyncio.exceptions.CancelledError: Cancelled by cancel scope 787b4e133e90
During handling of the above exception, another exception occurred:
+ Exception Group Traceback (most recent call last):
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/uvicorn/protocols/http/httptools_impl.py", line 409, in run_asgi
| result = await app( # type: ignore[func-returns-value]
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
| return await self.app(scope, receive, send)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/fastapi/applications.py", line 1054, in __call__
| await super().__call__(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/applications.py", line 112, in __call__
| await self.middleware_stack(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/middleware/errors.py", line 187, in __call__
| raise exc
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/middleware/errors.py", line 165, in __call__
| await self.app(scope, receive, _send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/middleware/cors.py", line 85, in __call__
| await self.app(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/middleware/exceptions.py", line 62, in __call__
| await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
| raise exc
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
| await app(scope, receive, sender)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 715, in __call__
| await self.middleware_stack(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 735, in app
| await route.handle(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 288, in handle
| await self.app(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 76, in app
| await wrap_app_handling_exceptions(app, request)(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
| raise exc
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
| await app(scope, receive, sender)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/routing.py", line 74, in app
| await response(scope, receive, send)
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 261, in __call__
| async with anyio.create_task_group() as task_group:
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 767, in __aexit__
| raise BaseExceptionGroup(
| ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception)
+-+---------------- 1 ----------------
| Traceback (most recent call last):
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 264, in wrap
| await func()
| File "/home/owen/miniconda3/envs/aphrodite/lib/python3.11/site-packages/starlette/responses.py", line 245, in stream_response
| async for chunk in self.body_iterator:
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/endpoints/openai/serving_chat.py", line 319, in chat_completion_stream_generator
| async for res in result_generator:
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/common/utils.py", line 466, in iterate_with_cancellation
| item = await awaits[0]
| ^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 942, in generate
| async for output in await self.add_request(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 112, in generator
| raise result
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 54, in _log_task_completion
| return_value = task.result()
| ^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 809, in run_engine_loop
| result = task.result()
| ^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 735, in engine_step
| request_outputs = await self.engine.step_async(virtual_engine)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/async_aphrodite.py", line 388, in step_async
| self._process_model_outputs(ctx=ctx)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/aphrodite_engine.py", line 1008, in _process_model_outputs
| self.output_processor.process_outputs(
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/output_processor/single_step.py", line 91, in process_outputs
| return self._process_sequence_group_outputs(sequence_group, outputs[0],
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/engine/output_processor/single_step.py", line 204, in _process_sequence_group_outputs
| scheduler.fork_seq(parent, seq)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/scheduler.py", line 1333, in fork_seq
| self.block_manager.fork(parent_seq, child_seq)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block_manager_v2.py", line 327, in fork
| self.block_tables[child_seq.seq_id] = src_block_table.fork()
| ^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/block_table.py", line 208, in fork
| forked_blocks = self._allocator.fork(self._blocks[-1])
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/cpu_gpu_block_allocator.py", line 206, in fork
| return allocator.fork(last_block)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/prefix_caching_block.py", line 368, in fork
| source_blocks = get_all_blocks_recursively(last_block)
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 355, in get_all_blocks_recursively
| recurse(last_block, all_blocks)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 351, in recurse
| recurse(block.prev_block, lst)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 351, in recurse
| recurse(block.prev_block, lst)
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 351, in recurse
| recurse(block.prev_block, lst)
| [Previous line repeated 977 more times]
| File "/home/owen/aphro-latest/aphrodite-engine/aphrodite/processing/block/common.py", line 350, in recurse
| if block.prev_block is not None:
| ^^^^^^^^^^^^^^^^
| RecursionError: maximum recursion depth exceeded
+------------------------------------
INFO: Shutting down
INFO: Waiting for connections to close. (CTRL+C to force quit)
INFO: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 6 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 35.1%, CPU KV cache usage: 0.0%.
INFO: Prefix cache hit rate: GPU: 41.65%, CPU: 0.00%
INFO: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 6 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 35.1%, CPU KV cache usage: 0.0%.
INFO: Prefix cache hit rate: GPU: 41.65%, CPU: 0.00%
INFO: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 6 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 35.1%, CPU KV cache usage: 0.0%.
INFO: Prefix cache hit rate: GPU: 41.65%, CPU: 0.00%
Your current environment
🐛 Describe the bug
Random crashes with unclear cause. The log of the crash is shown below, this is with disable frontend multiprocessing and disable async output proc.
Start command is as shown here with a lot of lora loaded: