Hi, this is https://xitter.cf/t.co/EO7MXLjjSU official account. We build systems for efficient LLM serving, including KTransformers, Mooncake and AgentENV.
Beijing
Joined August 2018
- Tweets98
- Following109
- Followers1.2K
- Likes133
KVCache.AI retweeted
Full session, vLLM Office Hours #55: Mooncake + vLLM/llm-d deep dive: youtube.com/watch?v=RFyeBEy1…
Live every other Thursday: red.ht/office-hours
KVCache.AI retweeted
TokenSpeed is only two months old, yet over the past two weeks we've had the privilege of being the Day 0 inference partner for both @thinkymachines's Inkling and @Kimi_Moonshot's Kimi K3.
Grateful to both teams for their trust, and proud of what our small, fast-moving team has accomplished so far. 🚀
#Kimi #K3 #Inkling
huggingface.co/moonshotai/Ki…
thinkingmachines.ai/news/int…
RT @Kimi_Moonshot: 🥝 Meet Kimi K2.5, Open-Source Visual Agentic Intelligence.
🔹 Global SOTA on Agentic Benchmarks: HLE full set (50.2%), B…
KVCache.AI retweeted
MiniMax M2.1 is OPEN SOURCE: SOTA for real-world dev & agents
• SOTA on coding benchmarks (SWE / VIBE / Multi-SWE)
• Beats Gemini 3 Pro & Claude Sonnet 4.5
• 10B active / 230B total (MoE)
Not just SOTA,
faster to infer, easier to deploy,
and yes, you can even run it locally
Weights: huggingface.co/MiniMaxAI/Min…
