Muse Glimmer BF16 on one RTX PRO 6000

# Muse Glimmer 30B BF16 + DFlash on RTX PRO 6000

> A reproducible single-GPU deployment for Muse Glimmer 30B BF16 with DFlash
> speculative decoding, served through vLLM's OpenAI-compatible API.

[![Hardware](https://img.shields.io/badge/hardware-RTX_PRO_6000_Blackwell-76B900)](#hardware)
[![vLLM](https://img.shields.io/badge/vLLM-PR_%2351655-blue)](#runtime-provenance)
[![License](https://img.shields.io/badge/license-MIT-green)](LICENSE)

## What you get

- One NVIDIA RTX PRO 6000 Blackwell with 96 GB VRAM.
- Local Muse Glimmer 30B BF16 target weights.
- Optional Muse DFlash assistant with 16-token speculative blocks.
- Muse reasoning and automatic tool-call parsers.
- A CUDA 13.2 b12x image pinned by immutable digest.
- Minimal Muse compatibility overlays generated from the pinned image.
- Health, static validation, status, logs, and functional smoke commands.
- Backward-compatible endpoint `http://qwen36-27b:8000/v1` for containers on
  the existing `homelab-public` network.

This recipe keeps the legacy Qwen hostname and served-model alias by default so
existing clients do not need coordinated changes. DNS names are infrastructure,
not sworn testimony about which transformer lives inside the box.

## Status

The image contains native Muse target, assistant, reasoning, and tool-parser
support, but predates four DFlash compatibility fixes from vLLM PR #51655.
The bootstrap derives image-matched files from the pinned image and applies only
those fail-closed edits; it does not replace b12x modules with incompatible
upstream copies.

## Hardware

Validated target platform:

- NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition
- 96 GB VRAM
- NVIDIA CDI device `nvidia.com/gpu=all`
- Rootless Podman; Compose is optional
- Approximately 56 GB for BF16 target weights, plus draft and KV-cache memory

A lower-memory GPU requires quantized target weights and different memory
settings. YAML cannot negotiate with physics, despite its confidence.

## Prerequisites

Place the target and assistant under one model root:

```text
/var/home/bazzite/models/
├── Muse-Glimmer-30B/
└── Muse-Glimmer-30B-assistant/
```

The target directory must contain the model config, tokenizer, processor, chat
template, safetensor index, and all weight shards. The assistant directory is
required by the default DFlash configuration. Run `make prepare` to download
`meta-models/Muse-Glimmer