Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion experiments/agentcompany/openhands/requirements.txt
Original file line number Diff line number Diff line change
Expand Up @@ -189,7 +189,7 @@ uri-template==1.3.0
urllib3==2.2.2
uvicorn==0.32.0
uvloop==0.21.0
vllm==0.6.3.post1
vllm==0.23.0

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Update companion pins

This bump leaves the environment pinned to the old vLLM dependency set, so pip install -r requirements.txt can fail dependency resolution. vllm==0.23.0 requires newer companions including torch==2.11.0, torchaudio==2.11.0, torchvision==0.26.0, transformers>=4.56.0, and tokenizers>=0.21.1, but this file still pins torch==2.4.0+cu121, torchaudio==2.4.0+cu121, torchvision==0.19.0, transformers==4.46.2, and tokenizers==0.20.3. If dependencies are bypassed, vLLM can also run against an unsupported ABI/API stack and fail at import or runtime. Update the companion pins with this vLLM bump, or keep vLLM on a compatible 0.6.x version, so the experiment environment can resolve and vLLM's native kernels match the installed PyTorch build.

T-Rex Ran code and verified through T-Rex

Prompt To Fix With AI
This is a comment left during a code review.
Path: experiments/agentcompany/openhands/requirements.txt
Line: 192

Comment:
**Update companion pins**

This bump leaves the environment pinned to the old vLLM dependency set, so `pip install -r requirements.txt` can fail dependency resolution. `vllm==0.23.0` requires newer companions including `torch==2.11.0`, `torchaudio==2.11.0`, `torchvision==0.26.0`, `transformers>=4.56.0`, and `tokenizers>=0.21.1`, but this file still pins `torch==2.4.0+cu121`, `torchaudio==2.4.0+cu121`, `torchvision==0.19.0`, `transformers==4.46.2`, and `tokenizers==0.20.3`. If dependencies are bypassed, vLLM can also run against an unsupported ABI/API stack and fail at import or runtime. Update the companion pins with this vLLM bump, or keep vLLM on a compatible 0.6.x version, so the experiment environment can resolve and vLLM's native kernels match the installed PyTorch build.

How can I resolve this? If you propose a fix, please make it concise.

Fix in Cursor Fix in Claude Code Fix in Codex

wandb==0.17.3
watchfiles==0.24.0
wcwidth==0.2.13
Expand Down