---
type: "post"
id: "nvidia-released-flare-a-local-inference-server-for-594e36"
slug: "nvidia-released-flare-a-local-inference-server-for-594e36"
title: "NVIDIA released Flare , a local inference server for SM120/SM121 GPUs including DGX Spark and RTX Blackwell."
description: "NVIDIA has released Flare, an open-source local inference server for NVIDIA SM120 and SM121 GPUs."
retrieval_nugget: "NVIDIA has released Flare, an open-source local inference server for NVIDIA SM120 and SM121 GPUs."
published_at: "2026-10-22"
updated_at: "2026-10-22"
record_date: "2026-10-22"
date_kind: "published_at"
topics: ["harness-engineering","agent-runtime"]
entities: ["NVIDIA","Flare","DGX Spark","Ignition","Helios","PyTorch","vLLM"]
related_patterns: ["harness-architecture-outlives-model-choice"]
novelty_label: "new_fact"
what_changed: "NVIDIA’s Flare adds a distinct local inference server for SM120/SM121 GPUs, including DGX Spark and RTX Blackwell, beyond the prior coverage of local AI hardware and its software ecosystem."
prior_refs: ["memory:756a7d41-bfed-86fc-a1bb-060d37e04226","memory:710384ad-484e-8c65-ae53-6488683d0e50"]
source_url: "https://github.com/NVIDIA/flare-local-inference"
source_urls: ["https://github.com/NVIDIA/flare-local-inference"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:nvidia-released-flare-a-local-inference-server-for-594e36"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/nvidia-released-flare-a-local-inference-server-for-594e36/","markdown":"https://newruntime.com/posts/nvidia-released-flare-a-local-inference-server-for-594e36.md","json":"https://newruntime.com/posts/nvidia-released-flare-a-local-inference-server-for-594e36.json"}
---

# NVIDIA released Flare , a local inference server for SM120/SM121 GPUs including DGX Spark and RTX Blackwell.

## Retrieval answer

NVIDIA has released Flare, an open-source local inference server for NVIDIA SM120 and SM121 GPUs.

NVIDIA has released Flare, an open-source local inference server for NVIDIA SM120 and SM121 GPUs. The repository describes it as a research prototype for long conversations, coding agents, and repeated tool use, including compact systems such as DGX Spark. It is licensed under Apache-2.0.

Flare separates model preparation from serving. Its Ignition component uses PyTorch, Transformers, and FlashInfer/b12x to load models, tune kernels, compile forwards, and capture CUDA graphs. Helios, the serving runtime, is written in Rust and runs the resulting package without Python. The project also says it plans buffers and execution capacity ahead of time and handles conversation state alongside KV caches.

NVIDIA positions Flare as a focused option for selected models and local workloads, rather than a general-purpose serving engine. The README explicitly says it will not replace vLLM, which covers a broader range of models, hardware, and deployment patterns. The source does not establish benchmark performance, a production-readiness commitment, or the complete set of supported models and hardware configurations.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Harness Engineering](https://newruntime.com/topics/harness-engineering.md): Explore the harness-engineering topic hub.
- topic hub: [Agent Runtime](https://newruntime.com/topics/agent-runtime.md): Explore the agent-runtime topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)