-
## 🐛 Bug
## To Reproduce
Steps to reproduce the behavior:
1. mlc_llm convert_weight ./dist/models/Qwen2-1.5B-Instruct/ --model-type qwen2 --quantization q0f16 -o dist/Qwen2-1.5B-Instruct-…
-
### Expected behavior
generate a .so model file
### Actual behavior
report error:
tvm._ffi.base.TVMError: Traceback (most recent call last):
[bt] (8) /home/mlc-relax/relax/build/libtvm.so(t…
-
![图片](https://github.com/apache/tvm/assets/70245966/1e420e94-7e1a-47ed-90f8-72306dfe5c05)
Steps to reproduce the behavior:
git clone https://github.com/zkkli/I-ViT.git
Just follow the TVM_benchmark…
-
There's a line at the end of `tvm/Dockerfile` that makes no sense:
```
ln -s /opt/mlc-llm/3rdparty/tvm/3rdparty /usr/local/lib/python3.8/dist-packages/tvm/3rdparty
```
It doesn't run, probably r…
-
### Summary
It's quite painful to reimplement ~700 TVM instructions in each tool (disassembler, decompiler, etc). I'm proposing a declarative specification of all TVM instructions which could be used…
-
Hi,
Thank you for this nice repo.
I am trying to export pytorch model to TVM with this snippet of code
```python
import torch
import tvm.relay as relay
from yolox.exp import get_exp
e…
-
### Checklist
- [X] I've read the [contribution guidelines](https://github.com/autowarefoundation/autoware/blob/main/CONTRIBUTING.md).
- [X] I've searched other issues and no duplicate issues were…
-
Hello! Just wondering if there are plans to support syncing of audit findings?
-
When used on a block with a init statement, blockize creates a separate init block that is not discoverable by any means. This hinders further scheduling, like tensorizing the init block.
### Expec…
-
```txt
Traceback (most recent call last):
File "/usr/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.8/runpy.py"…