v2.5.2
Friedrich-M/UniMatev2.5.2May 26, 2026by Lightheartdevs
Upgrading?
AI Summary
Dream Server 2.5.2 resolves dashboard routing issues caused by stale container IPs and implements a CPU fallback for NVIDIA GPUs with less than 4GB VRAM.
Key Highlights
- Dashboard nginx re-resolves services via Docker DNS at request time
- Discrete NVIDIA GPUs with less than 4GB VRAM route to CPU/Tier 0 fallback
- Fixes crash-looping CUDA llama-server for small GPUs
- Passes full-model capabilities and lifecycle tests across all fleet hosts
New Features
- Dashboard DNS re-resolution fix
- GPU fallback routing for small VRAM
Full Release Notes
> **Deprecated (2026-10-04):** this release pins a `hermes-agent` image tag that no longer exists, so installing it fails. It is also affected by [GHSA-vqpg-pvjj-4cmq](https://github.com/Osmantic/ODS/security/advisories/GHSA-vqpg-pvjj-4cmq) and [GHSA-v3hj-52g2-2hmc](https://github.com/Osmantic/ODS/security/advisories/GHSA-v3hj-52g2-2hmc). Install from the [README](https://github.com/Osmantic/ODS#get-started) instead. ## Fixed - Dashboard nginx now re-resolves the `dashboard-api` service through Docker DNS at request time so lifecycle recreation cannot leave `/api/*` and Dream Talk routes pinned to a stale container IP. - Discrete NVIDIA GPUs with less than 4GB VRAM now route to the CPU/Tier 0 fallback by default instead of entering a green install with a crash-looping CUDA `llama-server`. ## Validation - Fleet test run on 2026-05-26 at commit `c1df395` passed User Green: true fresh install, product, full-model capabilities, lifecycle, and UI validation across tower2, Strix Halo, Spark, and M5 MacBook Pro. - Full-model capability probes passed on all 4 enabled hosts, including chat, search, files, code, 76 Hermes skills, Dream Talk SSE streaming, session pooling, SOUL.md context, and install-context grounding. - Distro lab passed 10/10 Docker lanes and 5/5 Incus VM lanes, and all 14 prior regression fixtures stayed green. ## Fleet Validation Receipt - Release tag: `v2.5.2` - Release stamp commit: `2d040dbd` - Product validation commit: `c1df395` - Fleet run: `2026-05-26T11-17-28Z` - Harness: `main@f064e42` with clean true-fresh-install behavior - Gate result: **User Green PASS** - Zero-prereq bootstrap: **6/6 PASS** - Install Green: **PASS** on all 4 enabled hosts - Product Green: **PASS** for services, APIs, Hermes, cloud contracts, and UI - Capability Green: **PASS** with full-model probes proven on all 4 enabled hosts - Lifecycle Green: **PASS** for reinstall, restart, and doctor on all 4 enabled hosts - Distro lab: **10/10 Docker lanes PASS**, **5/5 Incus VM lanes PASS** - Regression fixtures: **14/14 PASS** - Bugs opened by run: **0** Enabled fleet hosts: - `tower2`: NVIDIA Blackwell x86, `qwen3-coder-next-Q4_K_M.gguf`, full capabilities PASS - `strix-halo`: AMD/Lemonade, `Qwen3.6-35B-A3B-UD-Q4_K_M.gguf`, full capabilities PASS - `spark`: NVIDIA GB10 aarch64, `Qwen3.6-35B-A3B-UD-Q4_K_M.gguf`, full capabilities PASS - `m5-mbp`: Apple M5 Max, `Qwen3.6-35B-A3B-UD-Q4_K_M.gguf`, full capabilities PASS Notes: - Vision probes were deferred because `DREAM_FLEET_TALK_VISION=1` was not enabled. - The release tag includes only the metadata stamp after the validated product commit; it does not introduce installer, runtime, compose, GPU-routing, model-selection, or dashboard behavior changes beyond the fixes already validated at `c1df395`.
Related Repositories
public-apis/public-apis★ 491,256
A collective list of free APIs
NousResearch/hermes-agent★ 256,126
The agent that grows with you
yt-dlp/yt-dlp★ 200,304
A feature-rich command-line audio/video downloader
microsoft/markitdown★ 191,591
Python tool for converting files and office documents to Markdown.
Significant-Gravitas/AutoGPT★ 187,703
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.