RuntimeError: Cannot find a working triton installation.
AHDDHAWQH opened this issue · comments
Overriding config with config/train_shakespeare_char.py:
train a miniature character-level shakespeare model
good for debugging and playing on macbooks and such
out_dir = 'out-shakespeare-char'
eval_interval = 250 # keep frequent because we'll overfit
eval_iters = 200
log_interval = 10 # don't print too too often
we expect to overfit on this small dataset, so only save when val improves
always_save_checkpoint = False
wandb_log = False # override via command line if you like
wandb_project = 'shakespeare-char'
wandb_run_name = 'mini-gpt'
dataset = 'shakespeare_char'
gradient_accumulation_steps = 1
batch_size = 64
block_size = 256 # context of up to 256 previous characters
baby GPT model :)
n_layer = 6
n_head = 6
n_embd = 384
dropout = 0.2
learning_rate = 1e-3 # with baby networks can afford to go a bit higher
max_iters = 5000
lr_decay_iters = 5000 # make equal to max_iters usually
min_lr = 1e-4 # learning_rate / 10 usually
beta2 = 0.99 # make a bit bigger because number of tokens per iter is small
warmup_iters = 100 # not super necessary potentially
on macbook also add
device = 'cpu' # run on cpu only
compile = False # do not torch compile the model
tokens per iteration will be: 16,384
found vocab_size = 65 (inside data\shakespeare_char\meta.pkl)
Initializing a new model from scratch
number of parameters: 10.65M
num decayed parameter tensors: 26, with 10,740,096 parameters
num non-decayed parameter tensors: 13, with 4,992 parameters
using fused AdamW: True
compiling the model... (takes a ~minute)
C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\utils.py:1764: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:455.)
return node.target(*args, **kwargs)
Traceback (most recent call last):
File "D:\吴清寒的\nano\nanoGPT-master\nanoGPT-master\train.py", line 264, in
losses = estimate_loss()
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\吴清寒的\nano\nanoGPT-master\nanoGPT-master\train.py", line 224, in estimate_loss
logits, loss = model(X, Y)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\eval_frame.py", line 451, in _fn
return fn(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\convert_frame.py", line 921, in catch_errors
return callback(frame, cache_entry, hooks, frame_state, skip=1)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\convert_frame.py", line 786, in _convert_frame
result = inner_convert(
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\convert_frame.py", line 400, in _convert_frame_assert
return compile(
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\contextlib.py", line 79, in inner
return func(*args, **kwds)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\convert_frame.py", line 676, in compile
guarded_code = compile_inner(code, one_graph, hooks, transform)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\utils.py", line 262, in time_wrapper
r = func(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\convert_frame.py", line 535, in compile_inner
out_code = transform_code_object(code, transform)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\bytecode_transformation.py", line 1036, in transform_code_object
transformations(instructions, code_options)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\convert_frame.py", line 165, in fn
return fn(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\convert_frame.py", line 500, in transform
tracer.run()
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\symbolic_convert.py", line 2149, in run
super().run()
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\symbolic_convert.py", line 810, in run
and self.step()
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\symbolic_convert.py", line 773, in step
getattr(self, inst.opname)(inst)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\symbolic_convert.py", line 2268, in RETURN_VALUE
self.output.compile_subgraph(
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\output_graph.py", line 991, in compile_subgraph
self.compile_and_call_fx_graph(tx, pass2.graph_output_vars(), root)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\contextlib.py", line 79, in inner
return func(*args, **kwds)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\output_graph.py", line 1168, in compile_and_call_fx_graph
compiled_fn = self.call_user_compiler(gm)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\utils.py", line 262, in time_wrapper
r = func(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\output_graph.py", line 1241, in call_user_compiler
raise BackendCompilerFailed(self.compiler_fn, e).with_traceback(
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\output_graph.py", line 1222, in call_user_compiler
compiled_fn = compiler_fn(gm, self.example_inputs())
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\repro\after_dynamo.py", line 117, in debug_wrapper
compiled_gm = compiler_fn(gm, example_inputs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_init.py", line 1729, in call
return compile_fx(model, inputs, config_patches=self.config)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\contextlib.py", line 79, in inner
return func(*args, **kwds)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\compile_fx.py", line 1330, in compile_fx
return aot_autograd(
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\backends\common.py", line 58, in compiler_fn
cg = aot_module_simplified(gm, example_inputs, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_functorch\aot_autograd.py", line 903, in aot_module_simplified
compiled_fn = create_aot_dispatcher_function(
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\utils.py", line 262, in time_wrapper
r = func(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_functorch\aot_autograd.py", line 628, in create_aot_dispatcher_function
compiled_fn = compiler_fn(flat_fn, fake_flat_args, aot_config, fw_metadata=fw_metadata)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_functorch_aot_autograd\runtime_wrappers.py", line 443, in aot_wrapper_dedupe
return compiler_fn(flat_fn, leaf_flat_args, aot_config, fw_metadata=fw_metadata)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_functorch_aot_autograd\runtime_wrappers.py", line 648, in aot_wrapper_synthetic_base
return compiler_fn(flat_fn, flat_args, aot_config, fw_metadata=fw_metadata)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_functorch_aot_autograd\jit_compile_runtime_wrappers.py", line 119, in aot_dispatch_base
compiled_fw = compiler(fw_module, updated_flat_args)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\utils.py", line 262, in time_wrapper
r = func(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\compile_fx.py", line 1257, in fw_compiler_base
return inner_compile(
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\repro\after_aot.py", line 83, in debug_wrapper
inner_compiled_fn = compiler_fn(gm, example_inputs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\debug.py", line 304, in inner
return fn(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\contextlib.py", line 79, in inner
return func(*args, **kwds)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\contextlib.py", line 79, in inner
return func(*args, **kwds)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\utils.py", line 262, in time_wrapper
r = func(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\compile_fx.py", line 438, in compile_fx_inner
compiled_graph = fx_codegen_and_compile(
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\compile_fx.py", line 714, in fx_codegen_and_compile
compiled_fn = graph.compile_to_fn()
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\graph.py", line 1307, in compile_to_fn
return self.compile_to_module().call
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\utils.py", line 262, in time_wrapper
r = func(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\graph.py", line 1250, in compile_to_module
self.codegen_with_cpp_wrapper() if self.cpp_wrapper else self.codegen()
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\graph.py", line 1205, in codegen
self.scheduler = Scheduler(self.buffers)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\utils.py", line 262, in time_wrapper
r = func(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\scheduler.py", line 1267, in init
self.nodes = [self.create_scheduler_node(n) for n in nodes]
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\scheduler.py", line 1267, in
self.nodes = [self.create_scheduler_node(n) for n in nodes]
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\scheduler.py", line 1358, in create_scheduler_node
return SchedulerNode(self, node)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\scheduler.py", line 687, in init
self._compute_attrs()
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\scheduler.py", line 698, in _compute_attrs
group_fn = self.scheduler.get_backend(self.node.get_device()).group_fn
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\scheduler.py", line 2276, in get_backend
self.backends[device] = self.create_backend(device)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\scheduler.py", line 2268, in create_backend
raise RuntimeError(
torch._dynamo.exc.BackendCompilerFailed: backend='inductor' raised:
RuntimeError: Cannot find a working triton installation. More information on installing Triton can be found at https://github.com/openai/triton
Set TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information
You can suppress this exception and fall back to eager by setting:
import torch._dynamo
torch._dynamo.config.suppress_errors = True
(nanogpt_new) PS D:\吴清寒的\nano\nanoGPT-master\nanoGPT-master> python train.py config/train_shakespeare_char.py
Overriding config with config/train_shakespeare_char.py:
train a miniature character-level shakespeare model
good for debugging and playing on macbooks and such
out_dir = 'out-shakespeare-char'
eval_interval = 250 # keep frequent because we'll overfit
eval_iters = 200
log_interval = 10 # don't print too too often
we expect to overfit on this small dataset, so only save when val improves
always_save_checkpoint = False
wandb_log = False # override via command line if you like
wandb_project = 'shakespeare-char'
wandb_run_name = 'mini-gpt'
dataset = 'shakespeare_char'
gradient_accumulation_steps = 1
batch_size = 64
block_size = 256 # context of up to 256 previous characters
baby GPT model :)
n_layer = 6
n_head = 6
n_embd = 384
dropout = 0.2
learning_rate = 1e-3 # with baby networks can afford to go a bit higher
max_iters = 5000
lr_decay_iters = 5000 # make equal to max_iters usually
min_lr = 1e-4 # learning_rate / 10 usually
beta2 = 0.99 # make a bit bigger because number of tokens per iter is small
warmup_iters = 100 # not super necessary potentially
on macbook also add
device = 'cpu' # run on cpu only
compile = False # do not torch compile the model
tokens per iteration will be: 16,384
found vocab_size = 65 (inside data\shakespeare_char\meta.pkl)
Initializing a new model from scratch
number of parameters: 10.65M
num decayed parameter tensors: 26, with 10,740,096 parameters
num non-decayed parameter tensors: 13, with 4,992 parameters
using fused AdamW: True
compiling the model... (takes a ~minute)
C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\utils.py:1764: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:455.)
return node.target(*args, **kwargs)
Traceback (most recent call last):
File "D:\吴清寒的\nano\nanoGPT-master\nanoGPT-master\train.py", line 264, in
losses = estimate_loss()
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\吴清寒的\nano\nanoGPT-master\nanoGPT-master\train.py", line 224, in estimate_loss
logits, loss = model(X, Y)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\eval_frame.py", line 451, in _fn
return fn(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\convert_frame.py", line 921, in catch_errors
return callback(frame, cache_entry, hooks, frame_state, skip=1)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\convert_frame.py", line 786, in _convert_frame
result = inner_convert(
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\convert_frame.py", line 400, in _convert_frame_assert
return compile(
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\contextlib.py", line 79, in inner
return func(*args, **kwds)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\convert_frame.py", line 676, in compile
guarded_code = compile_inner(code, one_graph, hooks, transform)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\utils.py", line 262, in time_wrapper
r = func(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\convert_frame.py", line 535, in compile_inner
out_code = transform_code_object(code, transform)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\bytecode_transformation.py", line 1036, in transform_code_object
transformations(instructions, code_options)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\convert_frame.py", line 165, in fn
return fn(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\convert_frame.py", line 500, in transform
tracer.run()
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\symbolic_convert.py", line 2149, in run
super().run()
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\symbolic_convert.py", line 810, in run
and self.step()
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\symbolic_convert.py", line 773, in step
getattr(self, inst.opname)(inst)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\symbolic_convert.py", line 2268, in RETURN_VALUE
self.output.compile_subgraph(
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\output_graph.py", line 991, in compile_subgraph
self.compile_and_call_fx_graph(tx, pass2.graph_output_vars(), root)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\contextlib.py", line 79, in inner
return func(*args, **kwds)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\output_graph.py", line 1168, in compile_and_call_fx_graph
compiled_fn = self.call_user_compiler(gm)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\utils.py", line 262, in time_wrapper
r = func(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\output_graph.py", line 1241, in call_user_compiler
raise BackendCompilerFailed(self.compiler_fn, e).with_traceback(
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\output_graph.py", line 1222, in call_user_compiler
compiled_fn = compiler_fn(gm, self.example_inputs())
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\repro\after_dynamo.py", line 117, in debug_wrapper
compiled_gm = compiler_fn(gm, example_inputs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_init.py", line 1729, in call
return compile_fx(model, inputs, config_patches=self.config)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\contextlib.py", line 79, in inner
return func(*args, **kwds)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\compile_fx.py", line 1330, in compile_fx
return aot_autograd(
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\backends\common.py", line 58, in compiler_fn
cg = aot_module_simplified(gm, example_inputs, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_functorch\aot_autograd.py", line 903, in aot_module_simplified
compiled_fn = create_aot_dispatcher_function(
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\utils.py", line 262, in time_wrapper
r = func(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_functorch\aot_autograd.py", line 628, in create_aot_dispatcher_function
compiled_fn = compiler_fn(flat_fn, fake_flat_args, aot_config, fw_metadata=fw_metadata)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_functorch_aot_autograd\runtime_wrappers.py", line 443, in aot_wrapper_dedupe
return compiler_fn(flat_fn, leaf_flat_args, aot_config, fw_metadata=fw_metadata)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_functorch_aot_autograd\runtime_wrappers.py", line 648, in aot_wrapper_synthetic_base
return compiler_fn(flat_fn, flat_args, aot_config, fw_metadata=fw_metadata)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_functorch_aot_autograd\jit_compile_runtime_wrappers.py", line 119, in aot_dispatch_base
compiled_fw = compiler(fw_module, updated_flat_args)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\utils.py", line 262, in time_wrapper
r = func(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\compile_fx.py", line 1257, in fw_compiler_base
return inner_compile(
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\repro\after_aot.py", line 83, in debug_wrapper
inner_compiled_fn = compiler_fn(gm, example_inputs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\debug.py", line 304, in inner
return fn(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\contextlib.py", line 79, in inner
return func(*args, **kwds)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\contextlib.py", line 79, in inner
return func(*args, **kwds)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\utils.py", line 262, in time_wrapper
r = func(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\compile_fx.py", line 438, in compile_fx_inner
compiled_graph = fx_codegen_and_compile(
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\compile_fx.py", line 714, in fx_codegen_and_compile
compiled_fn = graph.compile_to_fn()
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\graph.py", line 1307, in compile_to_fn
return self.compile_to_module().call
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\utils.py", line 262, in time_wrapper
r = func(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\graph.py", line 1250, in compile_to_module
self.codegen_with_cpp_wrapper() if self.cpp_wrapper else self.codegen()
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\graph.py", line 1205, in codegen
self.scheduler = Scheduler(self.buffers)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_dynamo\utils.py", line 262, in time_wrapper
r = func(*args, **kwargs)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\scheduler.py", line 1267, in init
self.nodes = [self.create_scheduler_node(n) for n in nodes]
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\scheduler.py", line 1267, in
self.nodes = [self.create_scheduler_node(n) for n in nodes]
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\scheduler.py", line 1358, in create_scheduler_node
return SchedulerNode(self, node)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\scheduler.py", line 687, in init
self._compute_attrs()
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\scheduler.py", line 698, in _compute_attrs
group_fn = self.scheduler.get_backend(self.node.get_device()).group_fn
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\scheduler.py", line 2276, in get_backend
self.backends[device] = self.create_backend(device)
File "C:\Users\86178\anaconda3\envs\nanogpt_new\lib\site-packages\torch_inductor\scheduler.py", line 2268, in create_backend
raise RuntimeError(
torch._dynamo.exc.BackendCompilerFailed: backend='inductor' raised:
RuntimeError: Cannot find a working triton installation. More information on installing Triton can be found at https://github.com/openai/triton
Set TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information
You can suppress this exception and fall back to eager by setting:
import torch._dynamo
torch._dynamo.config.suppress_errors = True