Update usage of call_tir

[sudeepag]

Running the notebook currently throws the following error:

error: Undefined variable: linear0
 --> /tmp/ipykernel_195051/3764025160.py:58:30
    |  
 58 |              lv0 = R.call_tir(linear0, (x, w0, b0), (1, 128), dtype="float32")
    |                       

Based on the course notes, it appears that the API may have been changed to call_dps_packed, so updating the notebook to reflect the change.

cc @tqchen @jinhongyii @MasterJH5574

Preview

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[sudeepag]

Addresses #8.

[tqchen]

sorry i merged pre-maturely. actually call_tir is right, just that we need to have a cls prefix,

@tvm.script.ir_module
class MyModule:
   @T.prim_func
   def linear():


   @R.function
   def main(x)
         cls = MyModule
         R.call_tir(cls.linear, ...)

[tqchen]

@sudeepag can you send an update

[sudeepag]

@tqchen Thanks for clarifying. Yes, I will revert to call_tir with the prefix.