Individual skill
setup-evo2-remote-tool
Set up, launch, validate, and troubleshoot the Evo 2 ToolUniverse remote tool and optionally relay it through ToolUniverse Connect. Use when deploying or auditing this implementation.
skills/setup-evo2-remote-tool/SKILL.md
Source commit 5598a9fc97e32964fe9b703818e7d0747142f179
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 9, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 1,779
- Repository last updated
- Nov 8, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agents Repository topic
- reasoning-agent Repository topic
- reasoning-language-models Repository topic
- tool-use Repository topic
- ai-agents Repository topic
- ai-scientists Repository topic
- automated-science Repository topic
- co-pilot Repository topic
- co-scientist Repository topic
- ai-for-science Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 12,666 bytesSKILL.mdcore · 12,666 bytesSKILL.mdcore · 12,666 bytesSKILL.mdcore · 12,666 bytesSKILL.mdcore · 12,666 bytesSKILL.mdcore · 12,666 bytesSKILL.mdcore · 12,666 bytesSKILL.mdcore · 12,666 bytesSKILL.mdcore · 12,666 bytesSKILL.mdcore · 12,666 bytesSKILL.mdcore · 12,666 bytesSKILL.mdcore · 12,666 bytes
Read excerpt
# Set up Evo 2 as a remote tool
> Validation status (2026-10-01): Evo 2 7B ran on the NVIDIA GB10 (aarch64, cc 12.1) under the optimization kit's `exact` mode. Two things had to be built for this architecture and neither was optional: **flash-attn from source** (~2 h; `import evo2` does not survive its absence, because upstream's `vortex/model/rotary.py` imports it unguarded -- so `mode = "off"` would not have routed around it), and **a CUDA 12.9 ptxas** for Triton, whose bundled one tops out below this card. Verified on FOUR CONSECUTIVE IDENTICAL REQUESTS plus a mixed-shape sequence: 5.6-6.5 s per 1024 bp window after a 243 s first call that reads the 12.8 GiB checkpoint. Peak reserved 16.82 GiB at 1024 bp rising only to 19.98 at 8192 -- 1.19x over 8x the length, because a 7B parameter term dominates. **evo2_40b is not this provider**: 76.6 GiB of weights, two visible devices for vortex's layer split, and FP8 through Transformer Engine, none of which this host has. Public publication, cross-user isolation, concurrency, recovery and scoring quality are untested; keep this deployment private.
## Prerequisites
- Run from the ToolUniverse repository root on Linux with Python 3.12.3.
- A CUDA GPU is required. This provider holds its model resident between requests; CPU is not a target.
- Keep provider data, weights, caches, and credentials outside Git.
- Bind to loopback. A non-loopback bind requires TOOLUNIVERSE_API_TOKEN; never put it in arguments or results.
Run the standard-library contract check before downloading large dependencies:
~~~bash