Top Tweets for #xinference
Gheist steals GitHub secrets. Revoke tokens; rotate secrets. #Wiz #GitHub #Anthropic #HuggingFace #Groq #NVIDIA #AWS #Amazon #Google #Microsoft #HashiCorp #IBM #Xinference #Xorbits #Unitree #Leon #VulnCheck
https://t.co/dUvgCBMNjs
π We just shipped our latest Xagent release 0.6.0 β and instead of a plain changelog, we turned it into a blog + video walkthrough, all produced inside Xagent itself.
π§ No studio. No editing software. Just text in, content out. Watch how it works π
#Xagent #Xinference #AIAgents #ReleaseNotes #BuildWithAI
Critical supply chain attack hits Xinference (v2.6.0-2.6.2). TeamPCPβs malware siphons cloud credentials and MLOps secrets. Audit your MLOps pipeline today.
#Xinference #TeamPCP #SupplyChainAttack #MLOps #Python #CloudSecurity #InfoSec #PyPI
https://t.co/ePCRa37pLU
π¨ 600K+ downloads. One malicious package.
Malicious #Xinference versions hit PyPi
Obfuscated base64 payload executes on import β infostealer deployed
#TeamPCP named in code, but denies involvement
this is a developing story β follow for updates: https://t.co/rtdQqOzzeA
π Xinference v2.3.0 is here!
Weβve leveled up support for GLM-5, Kimi-K2.5, and MiniMax-M2.5 across vLLM, Transformers, and GGUF.
Plus, Qwen3.5 gets key compatibility fixes for rock-solid deployment.
Scale your AI inference with ease! π οΈβ¨ #AI #LLM #Xinference #Qwen
π Xinference v2.2.0 is out!
π§ New models: GLM-5, Kimi-K2.5, MiniMax-M2.5, Qwen3.5
β‘ vLLM support for GLM-5 & Kimi-K2.5
π Bug fixes & cleaner exception handling
π’ Enterprise: Enhanced PPU scheduling
π€ XAgent v0.1.2 now with PPT generation
Upgrade nowοΌ
#Xinference #AI
π Xinference v2.1.0 is officially out!
π Experience the power of GLM-4.7 & GLM-4.7-Flash, elite speech-to-text with Qwen3-ASR (0.6B/1.7B), and stunning image gen via FLUX.2-Klein (4B/9B).
Plus, we've optimized MinerU2.5.
Upgrade now! π οΈβ¨
#AI #LLM #Xinference
π Xinference v1.16.0 is out!
Now with support for VACC GPUs and Continuous Batching for Apple MLX, boosting inference performance.π
Also adds new models like Qwen-Image-Layered.
Experience the next generation of inference performance!π
#Xinference #AI #MachineLearning
π Xinference v1.13.0 is here!
Model Hub is LIVE at https://t.co/V9dZcsEaSi β get the latest models instantly, no more waiting for releases!π
Plus: auto-batch embeddings = 10x faster throughput with ZERO code changes.
Just send requests, we batch magically!β‘
#Xinference #LLM
π Xinference v1.11.0.post1 is HERE! π₯
Added Qwen3-4B Instruct/Thinking & MiniCPM-V 4.5!
VLLM supercharged: multi-model loading (Omni/image/video/audio), AWQ 8bit quant, CUDA 12.8 v0.10.2!
OpenAI Image Edit API for epic editing/generation! #Xinference #AI
π Security upgrade!
The new IP whitelist feature lets you configure allowed source IPs via the XINFERENCE_ALLOWED_IPS environment variable, significantly boosting your deployment's security.
πPlus, OpenAI API gets JSON format support!
#Xinference #AI #API
π Xinference v1.9.0 is here and it's HUGE!
We've got gpt-oss, Qwen-Image, and DeepSeek R1 with Function Calling! Rerank models now switch backends on the fly (vLLM included!), and sglang streams function calls.
Time to upgrade your AI pipeline! β¨
#Xinference #AI
Exciting Updates from Xinference v1.8.1!π
Full support for GLM 4.5 series & Qwen3 models, experimental CUDA 12.8 image release (v1.8.1-cu128), πand automatic max supported length usage when max_tokens not set.
#Xinference #Update π
Exciting update from Xinference v1.6.1! π
π₯³Introducing Deepseek-R1-0528 & Qwen3 support, revamped Transformers VL model logic for continuous batching, and llama.cpp's Auto NGL for enhanced GPU deployment stability. β¨οΈ
Empowering AI capabilities! #Xinference #AI #Update π§ π§©
π₯³Exciting news! Xinference v1.5.1 is here!π
π§ Dive into Qwen3/Qwen3-MOE large model and explore Wan 2.1 text-to-video modeling for cutting-edge
Al video creation!π
π‘Experience VLLM's GGUFV2 format support with
stronger capabilities! #Xinference #Al
π Big news! #Xinference v1.3.0.post1 is out!
Now, distribute DeepSeek V3/R1 across multiple machinesβno Enterprise edition needed!
π₯οΈοΏ½οΏ½ Enhanced UI, 1-click DeepSeek, & new tools make it a breeze.
Next up: vLLM & MLX for even better performance! #AI #TechUpdate
π Xinference v1.2.1 released!
π Experience new models, features, and optimizations!
Community Edition Update: Use pip with 'pip install xinference==1.2.1' or pull the latest Docker image. #Xinference #AI
π₯ Xinference v1.2.0 update is here!
π Introducing vLLM-enhanced Xavier, supporting KV Cache sharing for faster inference in dialog scenarios. New models like Multimodal CogAgent and Marco-O1. Enhanced Image and Video models. π #Xinference #AI #Update
π Exciting news! Xinference v1.1.0 is here!
π New models include π€ llama-3.3-instruct, ποΈ f5-tts, and πΌοΈ jina-clip-v2.
Plus, enjoy features like Qwen2-vl support for MLX engine and optimized error message displays! #AI #Xinference
π Exciting news! β¨ Xinference v1.0.1 is here! Check out the new Qwen O1 series models π€ QwQ-32B-Preview & πΌοΈ glm-edge-chat.
Plus, enjoy new features like vllm engine support, Fish Speech updates, and Whisper for Mac MLX! #AI #UPDATE #Xinference #tech
Trends for you
Most Popular Users
Elon Musk 
@elonmusk
241.5M followers
Barack Obama
@barackobama
118.8M followers
Cristiano Ronaldo
@cristiano
114.5M followers
Donald J. Trump
@realdonaldtrump
111.9M followers
Narendra Modi
@narendramodi
107.1M followers
Rihanna
@rihanna
98.7M followers
NASA
@nasa
92.3M followers
Justin Bieber
@justinbieber
91.8M followers
KATY PERRY
@katyperry
90M followers
Taylor Swift
@taylorswift13
84M followers
Lady Gaga
@ladygaga
75.5M followers
Virat Kohli
@imvkohli
73.5M followers
Kim Kardashian
@kimkardashian
70.9M followers
YouTube
@youtube
68.8M followers
Neymar Jr
@neymarjr
66.5M followers
Bill Gates
@billgates
65.3M followers
Selena Gomez
@selenagomez
63.1M followers
The Ellen Show
@theellenshow
62.2M followers
CNN
@cnn
61.7M followers
X
@x
60.7M followers