You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by "Hzfengsy (via GitHub)" <gi...@apache.org> on 2025/03/03 10:13:19 UTC
[PR] [relax] Fix tree attention for Qwen2-1.5 models [tvm]
Hzfengsy opened a new pull request, #17700:
URL: https://github.com/apache/tvm/pull/17700
Fix the compilation error(https://github.com/mlc-ai/mlc-llm/issues/3143) for Qwen2-1.5 models in the tree attention implementation for vulkan backend.
cc @spectrometerHBH @vinx13
--
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: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [relax] Fix tree attention for Qwen2-1.5 models [tvm]
Posted by "MasterJH5574 (via GitHub)" <gi...@apache.org>.
MasterJH5574 merged PR #17700:
URL: https://github.com/apache/tvm/pull/17700
--
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: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [relax] Fix tree attention for Qwen2-1.5 models [tvm]
Posted by "Hzfengsy (via GitHub)" <gi...@apache.org>.
Hzfengsy commented on PR #17700:
URL: https://github.com/apache/tvm/pull/17700#issuecomment-2693887042
One additional note: this PR provides an immediate fix for the issue, but it doesn't address the underlying problem - the simplifier can potentially cause integer overflow. For illustration, here's a minimal reproducible example:
```python
import tvm
x = tvm.tir.Var("x", "int32")
# Creating an expression that triggers integer overflow during simplification
expr = (tvm.tir.Div(x + 1073741826, 3) - 357913942) * 1536
ana = tvm.arith.Analyzer()
print(ana.simplify(expr))
```
cc @tqchen
--
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: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org