v0.1.6 release - #68
Merged
Merged
Conversation
xysmlx
force-pushed
the
release_v0.1.6
branch
from
September 24, 2026 15:17
a87fd13 to
b1e0934
Compare
Sync the public sources with the tilert==0.1.6.post2 wheel on PyPI, which adds GLM-5.2/5.3 on AMD Instinct MI350X/MI355X (ROCm) next to the CUDA backends, plus PD disaggregation updates. - tilert/: Python sources recovered from the wheel, which ships them without docstrings or comments; formatted with isort/black/pyupgrade, with the repo's earlier lint suppressions restored where the code is unchanged. - tilert/generate.py: fix `python -m tilert.generate` for the CUDA models (deepseek_v3_2, glm5), which failed after loading the weights with "TypeError: generate() got an unexpected keyword argument 'max_new_tokens'". The fix is not in a published wheel yet. - .flake8 / pyproject.toml: relax flake8 and mypy per exported path, since per-line suppressions are not available in the wheel sources. - pyproject.toml / requirements.txt: torch>=2.11,<2.13 (CUDA backends need torch 2.11.0+cu130, the ROCm backend torch 2.12.0+rocm7.14.0), safetensors, and a `pd` extra for the router and decode server. - README: AgentX news, NVIDIA/AMD install matrix and ROCm image, GLM-5.2/5.3 weight conversion, the new CLI flags, PD additions, and the MI350X benchmark chart. Co-authored-by: Guojun Chen <gjchen@live.com> Co-authored-by: Yuxiao Guo <yuxiao.guo@outlook.com> Co-authored-by: Yuqing Xia <Xiayuqing0622@outlook.com> Co-authored-by: Jilong Xue <xuejilong@gmail.com> Co-authored-by: Ying Cao <lcy.seso@gmail.com> Co-authored-by: Heng Liu <18821707235@163.com> Co-authored-by: Zheng QiHang <zhengqihang0915@qq.com> Co-authored-by: Ziming Miao <mzmssg@gmail.com> Co-authored-by: Shuang Wu <WuSEmma@163.com> Co-authored-by: Baijie Xie <xbj0220ok@gmail.com>
xysmlx
force-pushed
the
release_v0.1.6
branch
from
September 24, 2026 15:18
b1e0934 to
8048d77
Compare
xiayuqing0622
approved these changes
Sep 24, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds GLM-5.2/5.3 on AMD Instinct MI350X/MI355X (ROCm), plus PD disaggregation updates.