---
type: "post"
id: "hy-nomas-inference-adds-nvidia-b300-support-and-ac70b7"
slug: "hy-nomas-inference-adds-nvidia-b300-support-and-ac70b7"
title: "Hy-Nomas inference adds NVIDIA B300 support and tensor parallelism"
description: "Tencent’s Hy-Nomas repository now documents NVIDIA B300 inference and adds tensor-parallel configuration alongside sequence-parallel work."
retrieval_nugget: "Tencent’s Hy-Nomas repository now documents NVIDIA B300 inference and adds tensor-parallel configuration alongside sequence-parallel work. For teams operating the video-generation system, the practical change is a documented way to divide dense model computation across GPUs, including an SP=1, TP=8 preset and explicit distributed-launch checks."
published_at: "2026-11-16"
updated_at: "2026-11-16"
record_date: "2026-11-16"
date_kind: "published_at"
topics: ["inference"]
entities: ["Tencent","Hy-Nomas","NVIDIA B300","NVIDIA GeForce RTX 4090"]
related_patterns: ["agent-economics-moves-to-completed-work"]
novelty_label: "new_fact"
what_changed: "Hy-Nomas adds NVIDIA B300 support and tensor parallelism, extending its existing SGLang serving and video-generation integrations."
prior_refs: ["https://newruntime.com/posts/tencent-adds-official-sglang-inference-instructions-for-hy-752130/","https://newruntime.com/posts/sglang-merges-hy-nomas-support-for-offline-and-372c96/"]
source_url: "https://github.com/Tencent-Hunyuan/Hy-Nomas/commit/d91fc49cd678b5aacd53f9fb2f9770258e540d41"
source_urls: ["https://github.com/Tencent-Hunyuan/Hy-Nomas/commit/d91fc49cd678b5aacd53f9fb2f9770258e540d41"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:hy-nomas-inference-adds-nvidia-b300-support-and-ac70b7"
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/hy-nomas-inference-adds-nvidia-b300-support-and-ac70b7/","markdown":"https://newruntime.com/posts/hy-nomas-inference-adds-nvidia-b300-support-and-ac70b7.md","json":"https://newruntime.com/posts/hy-nomas-inference-adds-nvidia-b300-support-and-ac70b7.json"}
markdown_url: "https://newruntime.com/posts/hy-nomas-inference-adds-nvidia-b300-support-and-ac70b7.md"
---

# Hy-Nomas inference adds NVIDIA B300 support and tensor parallelism

## Retrieval answer

Tencent’s Hy-Nomas repository now documents NVIDIA B300 inference and adds tensor-parallel configuration alongside sequence-parallel work. For teams operating the video-generation system, the practical change is a documented way to divide dense model computation across GPUs, including an SP=1, TP=8 preset and explicit distributed-launch checks.

## Summary
Tencent’s Hy-Nomas repository now documents NVIDIA B300 inference and adds tensor-parallel configuration alongside sequence-parallel work. For teams operating the video-generation system, the practical change is a documented way to divide dense model computation across GPUs, including an SP=1, TP=8 preset and explicit distributed-launch checks.

## What happened
Tencent’s GitHub commit for Hy-Nomas is titled “inference: 1) add B300 support; 2) SP perf optim; 3) add TP support.” It changes inference code, distributed utilities, launch scripts, tests, application code, and documentation. The update is a repository-level implementation change rather than a hosted-product release, pricing announcement, or change in model access.

The README’s standard inference example now passes `--sp-size 1 --tp-size 8`. Tencent’s documentation describes this preset as tensor-sharding dense DiT attention and MLP projections over eight ranks. It directs operators to a tensor-parallel inference guide for topology overrides, tests, and current limitations. This makes tensor parallelism an exposed deployment control in the documented path, rather than an implementation detail hidden behind a fixed launch arrangement.

Tencent also wires those controls into the Gradio application. Its command-line interface accepts `--sp-size` and `--tp-size`, transfers them to the parallelism configuration, and validates them against the distributed world size. For a Gradio deployment, the code raises an error unless `WORLD_SIZE` equals `sp_size * tp_size`. When more than one process is used, the application initializes a world mesh; it also records both settings in inference metadata.

Several launch examples move from sequence parallelism alone to a combination of sequence and tensor parallelism. The application documentation uses two hosts with eight GPUs each as an example, configured with `--sp-size 2 --tp-size 8`. It says that `sp_size × tp_size` should equal the host count multiplied by `NPROC_PER_NODE`. The commit adds a `TP_SIZE` environment-variable override and distributed tensor-parallel tests, as well as B300-specific inference code and a B300 input utility.

The README continues to identify a low-memory inference configuration for a single NVIDIA GeForce RTX 4090. That path and the new B300 work describe two different deployment targets: a single-card configuration for lower-memory use and distributed configuration for multi-GPU execution. Tencent’s primary announcement is the [Hy-Nomas commit d91fc49](https://github.com/Tencent-Hunyuan/Hy-Nomas/commit/d91fc49cd678b5aacd53f9fb2f9770258e540d41).

## What the archive adds
New Runtime covered [Tencent’s official SGLang inference instructions for Hy-Nomas](https://newruntime.com/posts/tencent-adds-official-sglang-inference-instructions-for-hy-752130/) on 2026-11-01. This is a new event in the same project: the earlier note concerned a documented SGLang usage path, while this commit adds B300 targeting and tensor-parallel inference configuration.

## Trend signal
This update weakly supports [agent economics moves to completed work](https://newruntime.com/patterns/agent-economics-moves-to-completed-work/). Distributing generation inference across GPUs is an engineering route to making workloads operationally feasible. But Tencent’s commit does not state cost per completed task, fleet-level throughput, or a comparison of completed-generation economics, so it is not evidence of a shift in the metric teams should optimize.

## Connections to other events
An earlier New Runtime note from 2026-11-06 covered [Hyperstition’s Hyperkernel release for NVIDIA B300](https://newruntime.com/posts/hyperstition-open-sources-hyperkernel-megakernels-for-nvidia-b300-1028a1/). Both events target the same hardware generation, but at different layers: Hyperkernel concerns GPU kernels, while Tencent’s change exposes B300 support and parallelism controls in a video-model inference stack.

## Why it matters
For teams operating Hy-Nomas, the immediate value is a clearer topology contract. Operators can configure sequence and tensor parallelism together instead of treating sequence parallelism as the sole visible setting in the launch examples. The documented two-host example and the `WORLD_SIZE` validation give a concrete starting point for composing a process group, reducing the chance of a launch whose declared parallel dimensions do not match its actual worker count.

The single-RTX 4090 low-memory configuration also gives developers a named option for local evaluation before committing a multi-GPU environment. Neither that configuration nor B300 support establishes that a particular prompt, video size, latency target, or output-quality requirement will work in a given deployment. The meaningful change is controllability: Hy-Nomas now makes the distribution dimensions explicit enough to test and tune.

## Limits and uncertainty
Tencent’s commit documents support and configuration, but it does not establish performance across different prompts, video sizes, hardware fleets, or operating conditions. The SP=1, TP=8 preset is a stated configuration, not a general speed or cost guarantee. Teams still need to consult the linked tensor-parallel guidance, validate their network and process topology, and run their own output-quality and latency tests.

The commit also does not state serving prices, B300 availability, comparative throughput, or fleet-level scaling results. Compatibility under alternative sequence- and tensor-parallel combinations remains a deployment question. The RTX 4090 low-memory path identifies a configuration to evaluate, not a promise that every Hy-Nomas workload fits or performs adequately on that card.

## Skill to build now
Turn parallelism settings into an explicit deployment check. Before launching a distributed Hy-Nomas job, calculate `sp_size * tp_size` from the intended topology and compare it with the actual `WORLD_SIZE`; use the two-host, eight-GPU-per-host example as a template only when its 16-process shape matches the cluster. Then run a fixed prompt set under at least two configurations and capture generation time, failures, GPU memory use, and output acceptance criteria. This separates a valid topology from a useful production configuration.

## Reader takeaway
Hy-Nomas now exposes tensor parallelism as a documented inference control, with an SP=1, TP=8 preset and B300-oriented code. Teams using the project should treat it as a concrete deployment option: match the process world to the parallelism dimensions, then measure the result on their own generation workload rather than assuming a universal performance gain.

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: [Inference](https://newruntime.com/topics/inference.md): Explore the inference topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Sources](https://newruntime.com/sources/): See the original sources this archive cites.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)
