#GPU performance optimization
912 related articles
Tech Frontiers·2 min
SGLang v0.5.12.post1 Released: DeepSeek V4 Stability Fixes and Blackwell Adaptation
SGLang v0.5.12.post1 stability patch details: 12 critical fixes covering DeepSeek V4 garbled text and crashes, NIXL PD disaggregated inference logic, Blackwell B300 adaptation, and cold start optimization.
Read more →
Tech Frontiers·2 min
LFM2.5-8B-A1B: A MoE Model with 1.5B Active Parameters Delivering 4x Its Weight Class Performance
Liquid AI releases LFM2.5-8B-A1B, a MoE model with 8B total params but only 1.5B active, matching 6B-class models in tool calling. Supports 128K context, local deployment, multilingual, with SGLang Day-0 support.
Read more →
Industry Insights·2 min
SGLang Enters Finance: How AI Inference Infrastructure Is Reshaping Wall Street
SGLang co-hosts a finance AI inference event with Crusoe AI and Cloudflare, exploring LLM inference deployment in trading, risk management, and compliance — signaling Wall Street's shift to production-grade AI infrastructure.
Read more →
Industry Insights·2 min
AMD MI355X Beats B200: Full-Stack Optimization Breakdown for 5% Lower TCO on DeepSeek-R1 Inference
AMD Instinct MI355X achieves 5% lower TCO than NVIDIA B200 on DeepSeek-R1 disaggregated inference via SGLang+MoRI full-stack optimization with 1.25x per-GPU throughput.
Read more →
Tech Frontiers·1 min
Cloudflare Contributes Critical KV Cache and Mooncake Fixes to SGLang
Cloudflare contributes decode KV cache offload and Mooncake recovery fixes to SGLang, resolving garbled output under high concurrency for Kimi K2.6 and enabling automatic fault recovery in distributed inference.
Read more →
Tech Frontiers·1 min
SGLang Hosts Agent Loops Office Hour, Focusing on Agentic Loop Architecture Optimization
SGLang team hosts an Agent Loops Office Hour exploring inference optimization for agentic loops, covering KV Cache reuse, low-latency multi-turn dialogue, and tool calling techniques.
Read more →
Product Reviews·3 min
Llama 3.3 70B In-Depth Review: Testing the Strongest Open-Source LLM with 13 Questions
Meta releases Llama 3.3 70B open-source model with just 70B parameters rivaling 405B performance. Tested on 13 logic, math, and coding questions, it passed 12 — reshaping the open-source model landscape.
Read more →
Tutorials·3 min
DeepSeek V4 Flash MTP Speculative Decoding Real-World Test: A Guide to 20% Faster Local Inference
Real-world testing of DeepSeek V4 Flash with MTP speculative decoding: ~20% speedup for code generation, minimal gains for text. Covers memory overhead, accuracy differences, Q4 vs Q3 quantization, and full deployment tutorial.
Read more →
Tutorials·3 min
AI-Generated 2D Game Animations & Scenes: A Practical Guide for Indie Developers
Compare two AI approaches for 2D game character animation and learn how to create parallax scrolling scenes with AI tools for import into Godot engine—a cost-effective guide for indie developers.
Read more →
Tutorials·3 min
The Complete Guide to Spring AI: A Full Learning Path for Java Engineers Building AI Applications
A comprehensive guide to Spring AI covering LLM integration, prompt engineering, RAG knowledge bases, and five AI Agent patterns, with three enterprise projects for Java engineers.
Read more →
Research·2 min
Meta Muse Spark Technical Deep Dive: How Three-Dimensional Scaling Achieves 10x Compute Reduction
Meta reveals Muse Spark technical details: three-dimensional scaling across pre-training, RL, and test-time inference achieves over 10x compute reduction versus Llama 4 Maverick.
Read more →
Industry Insights·3 min
Warp Bets on GPT-5.5: How AI Coding Agents Are Reshaping Open-Source Development Workflows
Warp deeply integrates GPT-5.5 to build cross-environment AI coding agents spanning local terminals, cloud deployment, and open-source collaboration. Explore its architecture, open-source strategy, and differentiation from GitHub Copilot.
Read more →
Tech Frontiers·1 min
DeepSeek V4-Pro Permanent Price Cut: Lower Developer Costs as LLM Price War Heats Up
DeepSeek announces permanent discount pricing for its V4-Pro model. Learn how this impacts developers, V4-Pro's competitive edge, and the latest LLM price war trends.
Read more →
Deep Dives·2 min
AI Agent Development Methodology: A Complete Guide from ReAct to Enterprise-Grade Tech Stack
A deep dive into AI Agent development methodology, from the ReAct theoretical framework to a four-layer enterprise tech stack covering model services, Agent types, LangChain, and production deployment.
Read more →
Tech Frontiers·3 min
Google Introduces AI Assistant in Job Interviews, OpenAI Launches Cybersecurity-Specific Model GPT-5.5 Cyber
Google introduces Gemini AI assistant in hiring to assess AI proficiency, OpenAI launches GPT-5.5 Cyber for critical infrastructure defense, Anthropic nears trillion-dollar valuation, Mozilla fixes 271 Firefox bugs with AI in two months.
Read more →
Industry Insights·2 min
NVIDIA Dynamo Snapshot: A Snapshot Recovery Solution for GPU Inference Cold Start Problems
Deep dive into how NVIDIA Dynamo Snapshot reduces LLM inference cold start time from minutes to seconds via GPU state snapshot and recovery, covering Kubernetes integration and elastic inference.
Read more →
Tech Frontiers·2 min
DeepSeek OCR2, Kimi K2.5, and Microsoft Maia 200 All Launched on the Same Day
DeepSeek releases OCR2 replacing CLIP with an LLM as visual encoder; Moonshot AI launches Kimi K2.5 with 100+ sub-agent cluster mode; Microsoft deploys 3nm Maia 200 chip; Alibaba releases Qwen3 Max Thinking.
Read more →
Product Reviews·2 min
Kimi K2.6 Open-Source Hands-On: How Strong Is Its Orchestration of 300 Concurrent Agents?
Deep analysis of Moonshot AI's open-source Kimi K2.6 Agent orchestration: 300 sub-Agents executing 4000-step tasks, outperforming GPT-5.4 in coding benchmarks, LoRA fine-tuning on 2x RTX 4090s.
Read more →
Product Reviews·3 min
AI Agent Investment Research Showdown: ChatGPT vs. Kimi vs. Manus — Who Delivers Better Financial Analysis?
Testing ChatGPT, Manus, and Kimi on the same investment analysis task reveals how multi-agent architecture, fault tolerance, and parallel workflows define the real capability boundaries of AI Agents in professional finance.
Read more →
Product Reviews·3 min
Running Qwen3.6-27B Locally on Mac: 4 Solutions Benchmarked
Benchmarking 4 solutions for running Qwen3.6-27B locally on Mac: GGUF, MLX Diflash, and MTP-LX. MTP-LX 4bit leads at 43.6 tok/s with solid coding, writing, and reasoning quality.
Read more →