Home Knowledge Base SGLang

SGLang

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Gemma 4 12B: A unified, encoder-free multimodal model

Introducing Gemma 4 12B: a unified, encoder-free multimodal model Today, we are introducing Gemma 4 12B, our latest model designed to bring agentic multimodal intelligence directly to laptops. Bridging the gap between our edge-friendly E4B and our more advanced 26B Mixture of Experts (MoE), Gemma 4 12B packages powerful capabilities inside a reduced memory footprint. It is also our first mid-sized model to feature native audio inputs.

Hacker News 7d ago

QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving

Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves large language model (LLM) answer quality by grounding generation in external evidence, but processing retrieved contexts makes the prefill stage a dominant serving cost. RAG cache fusion reduces this cost by reusing precomputed key-value (KV) caches for retrieved chunks and selectively recomputing tokens under the current prompt. Existing selectors, however, face a dilemma between quality and efficiency: fast...

arXiv CS 5d ago

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

Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency Since releasing Gemma 4 two months ago, we've been continuously working to expand its capabilities. First, we introduced Multi-Token Prediction (MTP) to accelerate inference, and just a couple of days ago, we released a 12B model to bridge the gap between our E4B and 26B MOE models. Today, we are releasing new checkpoints optimized with Quantization-Aware Training (QAT) to make Gemma 4 even more efficient, so...

Hacker News 5d ago

BlendServe: Optimizing Offline Inference for Auto-regressive Large Models with Resource-aware Batching

arXiv:2411.16102v2 Announce Type : replace Abstract: Offline batch inference, which leverages the flexibility of request batching to achieve higher throughput and lower costs, is becoming more popular for latency-insensitive applications. Meanwhile, recent progress in model capability and modality makes requests more diverse in compute and memory demands, creating unique opportunities for throughput improvement by resource overlapping.

arXiv CS 1d ago