tvm

tvm copied to clipboard

Bumps [urllib3](https://github.com/urllib3/urllib3) from 1.26.18 to 2.6.0. Release notes Sourced from urllib3's releases. 2.6.0 🚀 urllib3 is fundraising for HTTP/2 support urllib3 is raising ~$40,000 USD to release HTTP/2 support and...

dependabot[bot]

This PR supports NVRTC as an alternative to NVCC for faster, device-side JIT compilation of CUDA kernels, in favor of the PR [https://github.com/apache/tvm-ffi/pull/283](https://github.com/apache/tvm-ffi/pull/283). It enhances the CUDA compilation backend by:...

Kathryn-cat

[Bug] Error converting operator Attention

5

## 问题描述 在使用TVM 0.22.0版本导入ONNX模型（特别是使用opset 14的BGE模型）时，遇到了Attention操作符转换失败的问题。错误显示mask index形状不符合要求，即使已经尝试将所有mask相关输入设置为(batch_size, seq_len)的2D形状。 ## 环境信息 - TVM版本：0.22.0 - ONNX模型：BGE模型，opset 14 - 操作系统：Linux ## 错误详情 ### 完整错误堆栈 ``` Error converting operator Attention, with inputs: [lv8, metadata["relax.expr. Constant"][0] ...

caiyaodeng

[Relax][Torch] Fix from_exported_program crash with FakeTensor and lifted tensors

3

Fix Issue #18407: from_exported_program segfault with exported MHA using eq(0)/expand mask + in-place masked_fill_. Problem: When importing torch.export models with lifted tensors (e.g., from masked_fill_ operations), the conversion fails because...

Dayuxiaoshui

[CI] Update cpplint script to support revision-based linting

1

## What - update cpplint script to support revision-based linting

guan404ming

[CI] Move conda config files to tests/conda and remove unused conda build infrastructure

3

## Summary This PR reorganizes the conda-related files and removes unused conda build infrastructure. ## Changes ### Moved Files - `conda/build-environment.yaml` → `tests/conda/build-environment.yaml` - `conda/condarc` → `tests/conda/condarc` ### Removed Files...

tlopex

[Bug] Installation process incorrect/not working

4

Thanks for participating in the TVM community! We use https://discuss.tvm.ai for any general usage questions and discussions. The issue tracker is used for actionable items such as feature proposals discussion,...

michaelwcl

[Relax] Fix llama4_rope_with_position_map to support partial rotary factor

2

## Related Issue closes #17715 ## Why - Phi-4 uses: partial_rotary_factor = 0.75 (rotary_dim = 96) + longrope scaling - Longrope requires: Both long_factors + short_factors packed into one buffer...

guan404ming

[Feature Request] Support for sparse matrix multiplication and random number generation in PyTorch frontend

1

### Description When converting a PyTorch model containing sparse matrix multiplication (`torch.sparse.mm`) and random number generation (`torch.randn`) operations to TVM Relax module via `torch.export`, an AssertionError occurs. TVM currently does...

LiSsHhUuAaIi

[Build] Track upstream apache/tvm-ffi

1

DO NOT MERGE

junrushao