Red Hat AI (@RedHat

Red Hat AI

2,422 posts

Red Hat AI

@RedHat_AI

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

Joined May 2018

Replies Articles Media

Red Hat AI
@RedHat_AI
Jul 31
Speculators v0.7.0 is out. DSpark is now supported, and we shipped two DSpark speculators with it: GLM-5.2 and gemma-4-31B, both with strong gains over standard autoregressive drafting. Also new: a config-file-first training CLI, Muon as the default optimizer, and ~3x faster
Red Hat AI
@RedHat_AI
Jul 31
Kimi K3 now in NVFP4, the Blackwell counterpart to our FP8-Block checkpoint. MoE layers quantized to 4-bit for accelerated inference on Blackwell. Quality holds, GPQA 93.5 to 91.0. huggingface.co/RedHatAI/Kimi-…
Red Hat AI
@RedHat_AI
Jul 28
Running Kimi K3 on Hopper? We released an FP8-Block quantized checkpoint tuned for it. FP8 is native to Hopper's tensor cores, so you get the throughput the H100/H200 are built to deliver. Day Zero support ready with @vllm_project. Weights - try it now: huggingface.co/RedHatAI/Kimi-…
Red Hat AI
@RedHat_AI
Jul 30
The noisy-neighbor problem: Two teams share one model. One runs batch summarization, the other needs a live coding chatbot. The batch job saturates the GPU and the chatbot's time-to-first-token spikes. Flow control in @_llm_d_ fixes it with priority-based queuing and fairness
Optimize GPU efficiency with OpenShift AI and llm-d flow-control | Red Hat Developer
From developers.redhat.com
Red Hat AI
@RedHat_AI
Jul 29
Speculators and @vllm_project now support parallel drafting: P-EAGLE, DFlash, DSpark predict a whole block of draft tokens in one pass. No sequential penalty, still lossless. Blog: vllm.ai/blog/2026-07-2… DFlash on Qwen3-30B-A3B for coding, compared to EAGLE-3 and no spec:
Red Hat AI
@RedHat_AI
Jul 28
Kimi K3 open weights landed yesterday. By that afternoon, Red Hat AI Inference was serving it on one 8x B300 node. 2.8T params. Day-0 preview images exist so you can experiment the moment weights drop. 👇
Article
Run Kimi K3 on Day 0 with Red Hat AI. Here's the Exact Command.
Kimi K3 dropped open weights on July 27th. By that afternoon, we had it serving an OpenAI-compatible API on a single 8×B300 node using Red Hat AI Inference. This is the largest open-weight model ever...
See @RedHat_AI's full profile
Sign up
Log in

See @RedHat_AI's full profile