Red Hat AI's banner

Red Hat AI

@RedHat_AI • 12,621 subscribers

Accelerating AI innovation with open platforms and community. The future of AI is open.

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

What compression looks like on vLLM. Same Gemma 4 31B. Red Hat AI's quantized version runs at nearly 2x tokens/sec, half the memory, 99%+ accuracy retained. Open source. Quantized with LLM Compressor. Links in comments. 🙏 Sawyer Bowerman for the 2-minute demo.

What compression looks like on vLLM. Same Gemma 4 31B. Red Hat AI's quantized version runs at nearly 2x tokens/sec, half the memory, 99%+ accuracy retained. Open source. Quantized with LLM Compressor. Links in comments. 🙏 Sawyer Bowerman for the 2-minute demo.

34,260 次观看 • 5 个月前

Laguna XS.2 from Poolside is a 33B MoE built for agentic coding. Red Hat AI trained a DFlash speculator for it: 0.6B drafter, 8 tokens per pass, no quality loss. FP8, NVFP4, and INT4 checkpoints via LLM Compressor. Models in comments. Speedup with vLLM:

Laguna XS.2 from Poolside is a 33B MoE built for agentic coding. Red Hat AI trained a DFlash speculator for it: 0.6B drafter, 8 tokens per pass, no quality loss. FP8, NVFP4, and INT4 checkpoints via LLM Compressor. Models in comments. Speedup with vLLM:

21,590 次观看 • 4 个月前

Red Hat AI just shipped DFlash speculator checkpoints for two of NVIDIA AI's most powerful open models: → Nemotron Ultra 550B → Nemotron Super 120B On math and reasoning: ~5 out of 7 draft tokens accepted on average. On code (HumanEval): ~3.4 out of 7. Both checkpoints trained with the open source Speculators library from vLLM. Apache 2.0. Validated on NVIDIA B200. One flag to enable in vLLM: --spec-model RedHatAI/NVIDIA-Nemotron-3-Ultra-550B-A55B-speculator.dflash --spec-tokens 7 --spec-method dflash 🔗 Ultra 550B: 🔗 Super 120B:

Red Hat AI just shipped DFlash speculator checkpoints for two of NVIDIA AI's most powerful open models: → Nemotron Ultra 550B → Nemotron Super 120B On math and reasoning: ~5 out of 7 draft tokens accepted on average. On code (HumanEval): ~3.4 out of 7. Both checkpoints trained with the open source Speculators library from vLLM. Apache 2.0. Validated on NVIDIA B200. One flag to enable in vLLM: --spec-model RedHatAI/NVIDIA-Nemotron-3-Ultra-550B-A55B-speculator.dflash --spec-tokens 7 --spec-method dflash 🔗 Ultra 550B: 🔗 Super 120B:

15,077 次观看 • 2 个月前

Gemma 4 Diffusion landed in vLLM last week. Day 0. First diffusion LLM natively supported in vLLM. Instead of one token at a time, it predicts 256 tokens at once and iteratively denoises them in parallel. Result: 1,000+ tokens per second at batch size 1 on a single H100. Built on Model Runner V2. Google Gemma

Gemma 4 Diffusion landed in vLLM last week. Day 0. First diffusion LLM natively supported in vLLM. Instead of one token at a time, it predicts 256 tokens at once and iteratively denoises them in parallel. Result: 1,000+ tokens per second at batch size 1 on a single H100. Built on Model Runner V2. Google Gemma

17,670 次观看 • 3 个月前

Michael Goin (Misha Goin) walks through what's new in vLLM v0.17, v0.18, and v0.19 in ~8 minutes. Flash Attention 4, new performance modes, zero-bubble async scheduling, online MXFP4 quantization, Gemma 4, and a lot more. 1,592 commits. 682 contributors (163 new). 🎉 🚀

Michael Goin (Misha Goin) walks through what's new in vLLM v0.17, v0.18, and v0.19 in ~8 minutes. Flash Attention 4, new performance modes, zero-bubble async scheduling, online MXFP4 quantization, Gemma 4, and a lot more. 1,592 commits. 682 contributors (163 new). 🎉 🚀

23,127 次观看 • 5 个月前

Gemma 4 12B dropped today. Apache 2.0, multimodal: text, image, audio, and video. 256K context, built-in thinking, native tool calling. Running on Red Hat OpenShift AI with vLLM on Day 0:

Gemma 4 12B dropped today. Apache 2.0, multimodal: text, image, audio, and video. 256K context, built-in thinking, native tool calling. Running on Red Hat OpenShift AI with vLLM on Day 0:

15,995 次观看 • 4 个月前

InferenceMAX, vLLM TPU, compressed-tensors, MoE support via transformers, DeepSeek-OCR, and more. Here’s what’s new in the vLLM community over the past two weeks:

InferenceMAX, vLLM TPU, compressed-tensors, MoE support via transformers, DeepSeek-OCR, and more. Here’s what’s new in the vLLM community over the past two weeks:

24,429 次观看 • 11 个月前

A full year of vLLM in 30 minutes by vLLM Lead from UC Berkeley, Simon Mo. Model and hardware usage trends, model architectures, API evolution, V1 engine rebuild, multimodal progress, expanding hardware support, and more. Plus how we are thinking about 2026. Enjoy!

A full year of vLLM in 30 minutes by vLLM Lead from UC Berkeley, Simon Mo. Model and hardware usage trends, model architectures, API evolution, V1 engine rebuild, multimodal progress, expanding hardware support, and more. Plus how we are thinking about 2026. Enjoy!

15,717 次观看 • 9 个月前

没有更多内容可加载