LMSYS Blog · 实时热榜
- 01RadixArk Joins Forces with Google to Bring Full SGLang Features to TPUs - lmsys.org
RadixArk Joins Forces with Google to Bring Full SGLang Features to TPUs lmsys.org
最高第 1 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 02Towards Blackwell-Native 8-bit and 4-bit RL: End-to-End MXFP8 and NVFP4 RL in Miles - lmsys.org
Towards Blackwell-Native 8-bit and 4-bit RL: End-to-End MXFP8 and NVFP4 RL in Miles lmsys.org
最高第 2 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 03Toward a Cleaner Quantization Stack in SGLang - lmsys.org
Toward a Cleaner Quantization Stack in SGLang lmsys.org
最高第 3 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 04SGLang and Miles Add Day-0 Support for Kimi K3 - lmsys.org
SGLang and Miles Add Day-0 Support for Kimi K3 lmsys.org
最高第 4 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 05OPD Support in Miles - lmsys.org
OPD Support in Miles lmsys.org
最高第 5 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 06SGLang and Miles Add Day-0 Support for Inkling, a Frontier Multimodal Model - lmsys.org
SGLang and Miles Add Day-0 Support for Inkling, a Frontier Multimodal Model lmsys.org
最高第 6 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 07Serving GLM5.2 NVFP4 Agentic Workload with SGLang: Reaching 500 TPS in 2 Weeks - lmsys.org
Serving GLM5.2 NVFP4 Agentic Workload with SGLang: Reaching 500 TPS in 2 Weeks lmsys.org
最高第 7 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 08Bringing DeepSeek-V4 Flash RL Training to AMD Instinct MI355X GPUs with Miles - lmsys.org
Bringing DeepSeek-V4 Flash RL Training to AMD Instinct MI355X GPUs with Miles lmsys.org
最高第 8 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 09Accelerating SGLang HiCache with Netpreme X-Mem™ MPU - lmsys.org
Accelerating SGLang HiCache with Netpreme X-Mem™ MPU lmsys.org
最高第 9 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 10DSpark in SGLang: Speculative Decoding with Confidence-Driven, Variable-Length Verification - lmsys.org
DSpark in SGLang: Speculative Decoding with Confidence-Driven, Variable-Length Verification lmsys.org
最高第 10 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 11Agent-Assisted SGLang Development: An Initial Exploration - lmsys.org
Agent-Assisted SGLang Development: An Initial Exploration lmsys.org
最高第 11 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 12Improving DeepEP MoE Load Balance in SGLang with Waterfill and LPLB - lmsys.org
Improving DeepEP MoE Load Balance in SGLang with Waterfill and LPLB lmsys.org
最高第 12 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 13MOSS-TTS Local Transformer v1.5 on SGLang-Omni: Serving Native-Streaming 48 kHz Speech - lmsys.org
MOSS-TTS Local Transformer v1.5 on SGLang-Omni: Serving Native-Streaming 48 kHz Speech lmsys.org
最高第 13 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 14The next generation of speculative decoding: DFlash and Spec V2 - lmsys.org
The next generation of speculative decoding: DFlash and Spec V2 lmsys.org
最高第 14 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 15Announcing the Recipient of the 2026 LMSYS PhD Fellowship - lmsys.org
Announcing the Recipient of the 2026 LMSYS PhD Fellowship lmsys.org
最高第 15 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 16No Token Left Behind: Demystifying Token-In-Token-Out in Miles - lmsys.org
No Token Left Behind: Demystifying Token-In-Token-Out in Miles lmsys.org
最高第 16 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 17Higgs Audio v3 TTS on SGLang-Omni: Real-Time, Controllable Speech for Voice Agents - lmsys.org
Higgs Audio v3 TTS on SGLang-Omni: Real-Time, Controllable Speech for Voice Agents lmsys.org
最高第 17 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 18SGLang and Miles Add Day-0 Support for NVIDIA Nemotron 3 Ultra for Long-Running Autonomous Agents - lmsys.org
SGLang and Miles Add Day-0 Support for NVIDIA Nemotron 3 Ultra for Long-Running Autonomous Agents lmsys.org
最高第 18 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 19Heterogeneous CPU + GPU EPD Disaggregation to Boost VLM Serving - lmsys.org
Heterogeneous CPU + GPU EPD Disaggregation to Boost VLM Serving lmsys.org
最高第 19 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 20Win on TCO: How AMD Instinct™ MI355X Achieves Cost-Competitive Distributed Inference Through SGLang with MoRI - lmsys.org
Win on TCO: How AMD Instinct™ MI355X Achieves Cost-Competitive Distributed Inference Through SGLang with MoRI lmsys.org
最高第 20 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 21Updating 1T parameters in seconds — P2P weight transfer in Large Scale Distributed RL - lmsys.org
Updating 1T parameters in seconds — P2P weight transfer in Large Scale Distributed RL lmsys.org
最高第 21 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 22DeepSeek-V4 on Day 0: From Fast Inference to Verified RL with SGLang and Miles - lmsys.org
DeepSeek-V4 on Day 0: From Fast Inference to Verified RL with SGLang and Miles lmsys.org
最高第 22 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 23HiSparse: Turbocharging Sparse Attention with Hierarchical Memory - lmsys.org
HiSparse: Turbocharging Sparse Attention with Hierarchical Memory lmsys.org
最高第 23 名00:00 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 24
- 25Highlights of SGLang at NVIDIA GTC 2026 - lmsys.org
Highlights of SGLang at NVIDIA GTC 2026 lmsys.org
最高第 24 名14:27 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 26Elastic EP in SGLang: Achieving Partial Failure Tolerance for DeepSeek MoE Deployments - lmsys.org
Elastic EP in SGLang: Achieving Partial Failure Tolerance for DeepSeek MoE Deployments lmsys.org
最高第 25 名14:27 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 27ROCm Support for Miles: Large-Scale RL Post-Training on AMD Instinct™ GPUs - lmsys.org
ROCm Support for Miles: Large-Scale RL Post-Training on AMD Instinct™ GPUs lmsys.org
最高第 26 名14:27 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 28Unlocking 25x Inference Performance with SGLang on NVIDIA GB300 NVL72 - lmsys.org
Unlocking 25x Inference Performance with SGLang on NVIDIA GB300 NVL72 lmsys.org
最高第 27 名14:27 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 29Deploying DeepSeek on GB300 NVL72: Big Wins in Long-Context Inference - lmsys.org
Deploying DeepSeek on GB300 NVL72: Big Wins in Long-Context Inference lmsys.org
最高第 28 名14:27 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 30SGLang-Diffusion: Advanced Optimizations for Production-Ready Video Generation - lmsys.org
SGLang-Diffusion: Advanced Optimizations for Production-Ready Video Generation lmsys.org
最高第 29 名14:27 达到当日首次采集时已在榜当日结束时仍在榜累计约23小时48分 - 31Unleashing Computational Power: Ultimate Latency Optimization of Qwen3 and Qwen3-VL on AMD MI300X Series - lmsys.org
Unleashing Computational Power: Ultimate Latency Optimization of Qwen3 and Qwen3-VL on AMD MI300X Series lmsys.org
最高第 30 名14:27 达到14:27 首次观测上榜当日结束时仍在榜累计约9小时20分