Entries matching “nvidia”

PyTorch added end-to-end Muse Glimmer support to ExecuTorch; on an M5 Pro, DFlash speculative decoding lifts image+text decode from 21.6 to 33.0 tok/s, and it powers the Pi coding agent locally.

NVIDIA's technical blog reports Muse Glimmer serving over 20K tokens/sec on a single Blackwell Ultra GPU and covers RTX 5090, DGX Spark, DGX Station and Jetson deployments.

@homerquan

@homerquan

A start/stop/status launcher that serves the NVFP4 Muse Glimmer 30B checkpoint on NVIDIA DGX Spark with vLLM, Glimmer's reasoning and tool parsers, and its DFlash speculative decoder.

@sxuff

@sxuff

A pinned llama.cpp recipe for Muse Glimmer 30B on one NVIDIA GB10 that verifies Meta's official GGUFs by SHA-256 and reproduces text, tool-call, coding, vision and throughput checks.

@airawatraj

@airawatraj

Inference tuning notes for serving Muse Glimmer 30B NVFP4 with DFlash on a single NVIDIA DGX Spark as a consistent agent backend; the repo reports 27.5 tok/s average and 90/100 on its tool eval with 128K context.

Meta's launch post for Muse Glimmer, an Apache 2.0 30B model for local agents that fits in ~20GB at 4-bit and runs on M4/M5 Max Macs, RTX 5090s or 24–32GB GPUs.

NVIDIA's NVFP4-quantized version of Muse Glimmer 30B.

NVIDIA hosts a Muse Glimmer 30B endpoint on build.nvidia.com with Python (OpenAI, LangChain), JavaScript and curl examples for the ~29.6B multimodal model with 131K context.

@vcruz305

@vcruz305

Tested SGLang and vLLM launch recipes for an NVFP4 export of a Hermes-agentic fine-tune of Muse-Glimmer-30B on NVIDIA DGX Spark (GB10).

@dangkhoa2016

@dangkhoa2016

A self-hosted llama.cpp serving stack that runs Muse-Glimmer-30B GGUF with DFlash2 speculative decoding on Kaggle's NVIDIA T4 x2, exposed through an authenticated OpenAI-compatible gateway.

@chishiki37

@chishiki37

Benchmark reports on Muse-Glimmer-30B on NVIDIA DGX Spark covering BF16 to Q4 to DFlash (a 10x speedup) and NVFP4 via SGLang, plus a head-to-head against Qwen3.6-27B.

@High-Performance-AI-Lab

@High-Performance-AI-Lab

muser is a standalone inference engine for Muse Glimmer 30B on Apple Silicon Metal, with an optional disaggregated lane where an NVIDIA GB10 node prefills in NVFP4 and hands the KV cache to the Mac.