Phone model: xiaomi14pro
Memory: 16GB
After downloading the llama3 8B model, a CLANG compilation error was reported during loading. The specific logs are as follows:
Traceback (most recent call last):
File "/root/exo_master/exo/api/chatgpt_api.py", line 311, in handle_post_chat_completions
await self.node.process_prompt(shard, prompt, image_str, request_id=request_id)
File "/root/exo_master/exo/orchestration/standard_node.py", line 102, in process_prompt
resp = await self._process_prompt(base_shard, prompt, image_str, request_id, inference_state)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/exo_master/exo/orchestration/standard_node.py", line 140, in _process_prompt
result, inference_state, is_finished = await self.inference_engine.infer_prompt(request_id, shard, prompt, image_str, inference_state=inference_state)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/exo_master/exo/inference/tinygrad/inference.py", line 61, in infer_prompt
await self.ensure_shard(shard)
File "/root/exo_master/exo/inference/tinygrad/inference.py", line 95, in ensure_shard
self.model = build_transformer(model_path, shard, model_size="8B" if "8b" in shard.model_id.lower() else "70B")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/exo_master/exo/inference/tinygrad/inference.py", line 52, in build_transformer
load_state_dict(model, weights, strict=False, consume=False) # consume=True
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/nn/state.py", line 129, in load_state_dict
else: v.replace(state_dict[k].to(v.device)).realize()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/tensor.py", line 3186, in _wrapper
ret = fn(*args, *kwargs)
^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/tensor.py", line 204, in realize
run_schedule(self.schedule_with_vars(lst), do_update_stats=do_update_stats)
File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/engine/realize.py", line 220, in run_schedule
for ei in lower_schedule(schedule):
File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/engine/realize.py", line 213, in lower_schedule
raise e
File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/engine/realize.py", line 207, in lower_schedule
try: yield lower_schedule_item(si)
^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/engine/realize.py", line 191, in lower_schedule_item
runner = get_runner(si.outputs[0].device, si.ast)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/engine/realize.py", line 161, in get_runner
method_cache[ckey] = method_cache[bkey] = ret = CompiledRunner(replace(prg, dname=dname))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/engine/realize.py", line 83, in init
self.lib:bytes = precompiled if precompiled is not None else Device[p.dname].compiler.compile_cached(p.src)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/device.py", line 183, in compile_cached
lib = self.compile(src)
^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/runtime/ops_clang.py", line 10, in compile
subprocess.check_output(['clang', '-include', 'tgmath.h', '-shared', '-march=native', '-O2', '-Wall', '-Werror', '-x', 'c', '-fPIC', '-',
File "/root/miniconda3/envs/exo/lib/python3.12/subprocess.py", line 466, in check_output
return run(popenargs, stdout=PIPE, timeout=timeout, check=True,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/exo/lib/python3.12/subprocess.py", line 571, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['clang', '-include', 'tgmath.h', '-shared', '-march=native', '-O2', '-Wall', '-Werror', '-x', 'c', '-fPIC', '-', '-o', '/tmp/tmpg9zetteq']' returned non-zero exit status 1.
Phone model: xiaomi14pro Memory: 16GB After downloading the llama3 8B model, a CLANG compilation error was reported during loading. The specific logs are as follows:
Traceback (most recent call last): File "/root/exo_master/exo/api/chatgpt_api.py", line 311, in handle_post_chat_completions await self.node.process_prompt(shard, prompt, image_str, request_id=request_id) File "/root/exo_master/exo/orchestration/standard_node.py", line 102, in process_prompt resp = await self._process_prompt(base_shard, prompt, image_str, request_id, inference_state) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/exo_master/exo/orchestration/standard_node.py", line 140, in _process_prompt result, inference_state, is_finished = await self.inference_engine.infer_prompt(request_id, shard, prompt, image_str, inference_state=inference_state) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/exo_master/exo/inference/tinygrad/inference.py", line 61, in infer_prompt await self.ensure_shard(shard) File "/root/exo_master/exo/inference/tinygrad/inference.py", line 95, in ensure_shard self.model = build_transformer(model_path, shard, model_size="8B" if "8b" in shard.model_id.lower() else "70B") ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/exo_master/exo/inference/tinygrad/inference.py", line 52, in build_transformer load_state_dict(model, weights, strict=False, consume=False) # consume=True ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/nn/state.py", line 129, in load_state_dict else: v.replace(state_dict[k].to(v.device)).realize() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/tensor.py", line 3186, in _wrapper ret = fn(*args, *kwargs) ^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/tensor.py", line 204, in realize run_schedule(self.schedule_with_vars(lst), do_update_stats=do_update_stats) File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/engine/realize.py", line 220, in run_schedule for ei in lower_schedule(schedule): File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/engine/realize.py", line 213, in lower_schedule raise e File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/engine/realize.py", line 207, in lower_schedule try: yield lower_schedule_item(si) ^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/engine/realize.py", line 191, in lower_schedule_item runner = get_runner(si.outputs[0].device, si.ast) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/engine/realize.py", line 161, in get_runner method_cache[ckey] = method_cache[bkey] = ret = CompiledRunner(replace(prg, dname=dname)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/engine/realize.py", line 83, in init self.lib:bytes = precompiled if precompiled is not None else Device[p.dname].compiler.compile_cached(p.src) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/device.py", line 183, in compile_cached lib = self.compile(src) ^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/exo/lib/python3.12/site-packages/tinygrad/runtime/ops_clang.py", line 10, in compile subprocess.check_output(['clang', '-include', 'tgmath.h', '-shared', '-march=native', '-O2', '-Wall', '-Werror', '-x', 'c', '-fPIC', '-', File "/root/miniconda3/envs/exo/lib/python3.12/subprocess.py", line 466, in check_output return run(popenargs, stdout=PIPE, timeout=timeout, check=True, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/exo/lib/python3.12/subprocess.py", line 571, in run raise CalledProcessError(retcode, process.args, subprocess.CalledProcessError: Command '['clang', '-include', 'tgmath.h', '-shared', '-march=native', '-O2', '-Wall', '-Werror', '-x', 'c', '-fPIC', '-', '-o', '/tmp/tmpg9zetteq']' returned non-zero exit status 1.