yongwww commented on PR #16757:
URL: https://github.com/apache/tvm/pull/16757#issuecomment-2016558794
The mixtral compile using mlc-llm with the PR failed, resulting in the
following error:
```
Traceback (most recent call last):
File "<frozen runpy>", line 198, in _run_module_as_main
File "<frozen runpy>", line 88, in _run_code
File "/mlc-llm/python/mlc_llm/__main__.py", line 47, in <module>
main()
File "mlc-llm/python/mlc_llm/__main__.py", line 24, in main
cli.main(sys.argv[2:])
File "/mlc-llm/python/mlc_llm/cli/compile.py", line 128, in main
compile(
File "/mlc-llm/python/mlc_llm/interface/compile.py", line 232, in compile
_compile(args, model_config)
File "/mlc-llm/python/mlc_llm/interface/compile.py", line 178, in _compile
args.build_func(
File "/mlc-llm/python/mlc_llm/support/auto_target.py", line 242, in build
relax.build(
File "/tvm/python/tvm/relax/vm_build.py", line 335, in build
mod = pipeline(mod)
^^^^^^^^^^^^^
File "tvm/python/tvm/ir/transform.py", line 238, in __call__
return _ffi_transform_api.RunPass(self, mod)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "vm/python/tvm/_ffi/_ctypes/packed_func.py", line 239, in __call__
raise_last_ffi_error()
File "vm/python/tvm/_ffi/base.py", line 481, in raise_last_ffi_error
raise py_err
File "mlc-llm/python/mlc_llm/compiler_pass/pipeline.py", line 172, in
_pipeline
mod = seq(mod)
^^^^^^^^
File "tvm/python/tvm/ir/transform.py", line 238, in __call__
return _ffi_transform_api.RunPass(self, mod)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "tvm/python/tvm/ir/transform.py", line 307, in _pass_func
return inst.transform_module(mod, ctx)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "mlc-llm/python/mlc_llm/compiler_pass/dispatch_kv_cache_creation.py",
line 94, in transform_module
kwargs = extract_creation_args(creation_func)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "mlc-llm/python/mlc_llm/compiler_pass/dispatch_kv_cache_creation.py",
line 16, in extract_creation_args
assert len(func.body.blocks[0].bindings) == 2
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
