LMSYS Blog · 实时热榜
- 01HPC-Ops × SGLang: High-Performance Attention, Router GEMM, and MoE Kernels from Tencent Hunyuan - LMSYS Org
HPC-Ops × SGLang: High-Performance Attention, Router GEMM, and MoE Kernels from Tencent Hunyuan LMSYS Org
最高第 1 名00:23 达到00:23 首次观测上榜当日结束时仍在榜上榜 3 次（重入 2 次）累计约22小时8分 - 02Full-Stack Performance Optimization of AR+DiT in SGL-Diffusion - LMSYS Org
Full-Stack Performance Optimization of AR+DiT in SGL-Diffusion 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51分 - 03SpecForge v0.3.0: a Unified Disaggregated and Colocated Speculative Decoding Stack, and New Open SpecBundle Draft Models - LMSYS Org
SpecForge v0.3.0: a Unified Disaggregated and Colocated Speculative Decoding Stack, and New Open SpecBundle Draft Models 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51分 - 04RadixArk 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 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51分 - 05Towards 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 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51分 - 06Toward a Cleaner Quantization Stack in SGLang - LMSYS Org
Toward a Cleaner Quantization Stack in SGLang 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51分 - 07SGLang 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 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51分 - 08Serving 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51分 - 09Bringing 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51分 - 10OPD Support in Miles - LMSYS Org
OPD Support in Miles LMSYS Org
最高第 8 名10:31 达到10:31 首次观测上榜当日结束时仍在榜累计约13小时20分 - 11Accelerating 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51分 - 12SGLang 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 9 名18:47 达到18:47 首次观测上榜23:51 观测离榜上榜 5 次（重入 4 次）累计约2小时8分 - 13DSpark 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51分 - 14Agent-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51分 - 15Improving 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51分 - 16MOSS-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51分 - 17The 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51分 - 18No 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 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51分 - 19Higgs 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 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51分 - 20SGLang 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 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51分 - 21Heterogeneous CPU + GPU EPD Disaggregation to Boost VLM Serving - LMSYS Org
Heterogeneous CPU + GPU EPD Disaggregation to Boost VLM Serving 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51分 - 22Win 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 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51分 - 23Updating 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 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51分 - 24DeepSeek-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 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51分 - 25HiSparse: Turbocharging Sparse Attention with Hierarchical Memory - LMSYS Org
HiSparse: Turbocharging Sparse Attention with Hierarchical Memory 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51分 - 26Highlights of SGLang at NVIDIA GTC 2026 - LMSYS Org
Highlights of SGLang at NVIDIA GTC 2026 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51分 - 27Elastic 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 24 名00:00 达到当日首次采集时已在榜02:15 观测离榜上榜 3 次（重入 2 次）累计约1小时43分 - 28ROCm 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 25 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51分 - 29Unlocking 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 26 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51分 - 30Deploying 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 27 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51分 - 31SGLang-Diffusion: Advanced Optimizations for Production-Ready Video Generation - LMSYS Org
SGLang-Diffusion: Advanced Optimizations for Production-Ready Video Generation LMSYS Org
最高第 28 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51分 - 32Unleashing 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 29 名00:00 达到当日首次采集时已在榜当日结束时仍在榜上榜 6 次（重入 5 次）累计约21小时43分 - 33Squeezing 1TB Model Rollout into a Single H200: INT4 QAT RL End-to-End Practice - LMSYS Org
Squeezing 1TB Model Rollout into a Single H200: INT4 QAT RL End-to-End Practice LMSYS Org
最高第 30 名00:00 达到当日首次采集时已在榜10:31 观测离榜累计约10小时31分