corpus.blog
56,966 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a0823d-891e-70d0-b8c7-ee62795d238e

MiniMax H3 on vLLM-Omni: From System-Wide Optimization to Real-Time Serving with FastVideo’s FastH3

vLLM Blog · published 1 September 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at vllm.ai Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
75
Words captured
4,443

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://github.com/vllm-project/vllm-omni
github.com
https://github.com/hao-ai-lab/FastVideo
github.com
https://haoailab.com/blogs/fasth3-preview/
haoailab.com
https://huggingface.co/MiniMaxAI/MiniMax-H3
huggingface.co
https://github.com/vllm-project/vllm-omni/blob/main/recipes/MiniMaxAI/MiniMax-H3.md
github.com
https://huggingface.co/docs/diffusers/main/en/api/pipelines/minimax_h3
huggingface.co
https://github.com/vllm-project/vllm-omni/commit/b81aeb7b86837f6fe8956f3aef83798ad26c5a26
github.com
https://github.com/vllm-project/vllm-omni/commit/86b85c078bc041e04aee4c4d9167fb10fb1994c7
github.com
https://huggingface.co/MiniMaxAI/MiniMax-H3/tree/42ed227ee7df40d41602854ae760620d6eb651fe
huggingface.co
https://github.com/vllm-project/vllm-omni/blob/main/recipes/MiniMaxAI/MiniMax-H3-RTX-PRO-5000.md
github.com
https://github.com/vllm-project/vllm-omni/blob/main/recipes/MiniMaxAI/MiniMax-H3-4090.md
github.com
https://github.com/vllm-project/vllm-omni/blob/main/recipes/MiniMaxAI/MiniMax-H3-5090.md
github.com
https://github.com/vllm-project/vllm-omni/blob/main/recipes/MiniMaxAI/MiniMax-H3-Spark-GB10.md
github.com
https://github.com/vllm-project/vllm-omni/pull/5283
github.com
https://github.com/vllm-project/vllm-omni/pull/5779
github.com
https://github.com/vllm-project/vllm-omni/pull/6173
github.com
https://github.com/vllm-project/vllm-omni/pull/6340
github.com
https://github.com/vllm-project/vllm-omni/pull/5990
github.com
https://github.com/vllm-project/vllm-omni/pull/6281
github.com
https://github.com/vllm-project/vllm-omni/pull/6878
github.com
https://github.com/vllm-project/vllm-omni/pull/6283
github.com
https://github.com/vllm-project/vllm-omni/pull/6607
github.com
https://github.com/vllm-project/vllm-omni/pull/6824
github.com
https://github.com/vllm-project/vllm-omni/pull/6288
github.com
https://github.com/vllm-project/vllm-omni/pull/6499
github.com
https://github.com/vllm-project/vllm-omni/pull/6776
github.com
https://huggingface.co/MiniMaxAI/MiniMax-H3/resolve/main/assets/t2va.mp4
huggingface.co
https://vllm-project.github.io/assets/figures/2026-08-29-minimax-h3-production-serving/evidence/b300/trtllm_dense.mp4
vllm-project.github.io
Distributed Layerwise Offload: Scaling Toward 200B+ DiT Models Efficiently in vLLM-Omni Read at the source ↗
vllm.ai
https://github.com/vllm-project/vllm-omni/pull/5885
github.com
https://github.com/vllm-project/vllm-omni/issues/5707
github.com
https://github.com/vllm-project/vllm-omni/pull/5910
github.com
https://github.com/vllm-project/vllm-omni/pull/6162
github.com
https://github.com/hsliuustc0106/vllm-omni-cookbook/blob/main/blog/_posts/2026-08-18-online-quantization-fp8.md
github.com
https://github.com/hsliuustc0106/vllm-omni-cookbook/blob/main/blog/_posts/2026-08-16-understanding-pr-6162-svdquant-w4a4-blackwell.md
github.com
https://arxiv.org/abs/2512.12087
arxiv.org
https://github.com/vllm-project/vllm-omni/blob/main/docs/user_guide/diffusion/attention_backends/trtllm.md
github.com
https://github.com/vllm-project/vllm-omni/pull/5853
github.com
https://github.com/vllm-project/vllm-omni/pull/6279
github.com
https://github.com/vllm-project/vllm-omni/pull/5810
github.com
https://github.com/vllm-project/vllm-omni/issues/5700
github.com
https://github.com/vllm-project/vllm-omni/pull/6476
github.com
https://github.com/vllm-project/vllm-omni/pull/6550
github.com
https://github.com/vllm-project/vllm-omni/pull/6714
github.com
https://github.com/vllm-project/vllm-omni/pull/6909
github.com
https://github.com/vllm-project/vllm-project.github.io/pull/315
github.com
https://recipes.vllm.ai/MiniMaxAI/MiniMax-H3
recipes.vllm.ai
https://vllm-project.github.io/assets/figures/2026-08-29-minimax-h3-production-serving/fast-h3-5s.mp4
vllm-project.github.io
https://vllm-project.github.io/assets/figures/2026-08-29-minimax-h3-production-serving/fast-h3-10s.mp4
vllm-project.github.io
https://vllm-project.github.io/assets/figures/2026-08-29-minimax-h3-production-serving/fast-h3-15s.mp4
vllm-project.github.io
https://github.com/vllm-project/vllm-omni/issues/6872
github.com
https://github.com/vllm-project/vllm-omni/pull/6885
github.com
https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE
huggingface.co
https://github.com/verl-project/verl-omni
github.com
https://github.com/vllm-project/vllm-omni/pull/5851
github.com
https://github.com/Tencent-Hunyuan/UniRL
github.com
https://github.com/RLinf/RLinf
github.com
https://huggingface.co/FastVideo/FastVideo-FastH3-4-step-Preview-v1-LoRA
huggingface.co
https://github.com/Isotr0py
github.com
https://github.com/lishunyang12
github.com
https://github.com/evanchueng
github.com
https://github.com/Gaohan123
github.com
https://github.com/david6666666
github.com
https://github.com/gcanlin
github.com
https://github.com/yuanwu2017
github.com
https://github.com/bobboli
github.com
https://github.com/fan2956
github.com
https://github.com/mo-ke-ke
github.com
https://github.com/mglyn
github.com
https://github.com/MosCloud
github.com
https://github.com/ultism
github.com
https://github.com/princepride
github.com
https://github.com/NancyFyong
github.com
https://github.com/mengchengTang
github.com
https://huggingface.co/docs/diffusers/v0.40.0/api/pipelines/minimax_h3
huggingface.co