junrushao opened a new pull request, #14784:
URL: https://github.com/apache/tvm/pull/14784
This PR introduces a new user-facing API `tune_tir_module` that makes it
more convenient to feed in an IRModule consists of multiple TIRs and customize
the search space for them. This is widely used in our MLC-LLM project where we
wanted to customize the search space for some quantization-related operators.
An example usecase:
```python
from tvm import meta_schedule as ms
ms.tir_integration.tune_tir_module(
...
space="cuda", <========== by default, the space is "cuda" rather than
"cuda-tensorcore"
special_space={
"fused_decode1_fused_matmul2_add1_gelu": sch_fused_decode_gemv,
"decode": sch_decode,
},
)
```
--
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]
