Vllm

Feeds to Scour
SubscribedAll
Scoured 112 posts in 6.5 ms

Report: GKE Inference Gateway delivers up to 92% faster AI responses

 🤖LLM  Content type: Blog

WEKA software speeds long context AI inferencing on Oracle’s public cloud

 🤖Agents  Content type: News
blocksandfiles.com·

STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control

 🤖LLM Inference  Content type: Academic
arxiv.org·

What Arm-based innovations happened in May 2026?

 🤖LLM  Content type: Blog
newsroom.arm.com·

High Bandwidth Flash | A New Memory for AI Data Centers and Edge Computing | Sandisk

 🤖LLM Inference
ncnonline.net·

Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency

 🤖LLM  Content type: News  Content type: Blog
blog.google··Hacker News

libertywing/FlashMemory-Deepseek-V4: FlashMemory DS-V4 Retriever: a lightweight retriever that sparsifies DeepSeek-V4 CSA KV-cache. Weights available on Hugging Face.

 🤖LLM Inference  Content type: Code
github.com·

Where to Host Your Open-Source Model (Under 10B Parameters)

 🤖LLM
digitalocean.com·

Claude Fable 5 🚀, Gemini 3.5 Live Translate 📱, scaling test time compute 📈

 🤖LLM Inference
tldr.tech·

ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models

 🤖Agents  Content type: Academic
arxiv.org·

OpenCV 5.0 Computer Vision Library Released with Rewritten DNN Engine

 🤖LLM Inference
linuxiac.com·

OpenCV 5 release - New DNN engine with enhanced ONNX and LLM/VLM support, Intel, Arm, and RISC-V hardware optimizations - CNX Software

 🤖LLM  Content type: News
cnx-software.com·

Two Leaps to 1000 Tokens/s on a 1T-Parameter Model: On Inference Systems, Execution Boundaries, and Co-Design

 🤖LLM Inference  Content type: Blog
tilert.ai··Hacker News

IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference

 🤖Agents  Content type: Academic
arxiv.org·

From GPU to Token: The 8-Layer Observability Stack for AI Infrastructure

 🤖LLM  Content type: Blog
jimmysong.io·

huawei-csl/KVarN: KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.

 🤖LLM Inference  Content type: Code
github.com··Hacker News

BeeLlama.cpp DFlash on Strix Halo: 2.7x Gemma 31B, But MTP Is Still Faster

 🤖LLM Inference
sleepingrobots.com·

A system programmer’s guide to LLM inference

 🤖LLM Inference  Content type: Blog

DeepSeek V4, LeCun's Bet Against LLMs, and Lovable's Self-Improving Agent - The Tokenizer Edition #30

 🤖LLM

Clairvoyant: Predictive SJF Scheduling to Mitigate Head-of-Line Blocking in Serial LLM Backends

 🤖LLM Inference  Content type: Academic
arxiv.org·

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help