LMSYS Blog · 实时热榜
- 01
- 02Win 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48分 - 03Highlights of SGLang at NVIDIA GTC 2026 - lmsys.org
Highlights of SGLang at NVIDIA GTC 2026 lmsys.org
最高第 24 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 - 04DeepSeek-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48分 - 05Updating 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48分 - 06Heterogeneous 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48分 - 07Improving 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 10 名00:03 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 - 08Towards 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 - 09Deploying 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 8 名00:03 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 - 11Accelerating SGLang HiCache with Netpreme X-Mem™ MPU - lmsys.org
Accelerating SGLang HiCache with Netpreme X-Mem™ MPU lmsys.org
最高第 7 名00:03 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 - 12ROCm 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 - 13Serving 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 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 - 14RadixArk 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 - 15HiSparse: 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48分 - 16Unlocking 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 - 17SGLang 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 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 - 18SGLang 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 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 - 19Announcing the Recipient of the 2026 LMSYS PhD Fellowship - lmsys.org
Announcing the Recipient of the 2026 LMSYS PhD Fellowship 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 - 20No 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48分 - 21MOSS-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 11 名00:03 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 - 22Higgs 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48分 - 23OPD Support in Miles - lmsys.org
OPD Support 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48分 - 24SGLang 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48分 - 25Agent-Assisted SGLang Development: An Initial Exploration - lmsys.org
Agent-Assisted SGLang Development: An Initial Exploration lmsys.org
最高第 9 名00:03 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 - 26SGLang-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 - 27The 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 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 - 28Unleashing 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00:00 达到当日首次采集时已在榜21:23 观测离榜上榜 2 次（重入 1 次）累计约21小时8分 - 29Toward a Cleaner Quantization Stack in SGLang - lmsys.org
Toward a Cleaner Quantization Stack in SGLang lmsys.org
最高第 3 名03:47 达到03:47 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17小时52分 - 30Bringing 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 7 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14小时44分 - 31Elastic 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00:00 达到当日首次采集时已在榜当日结束时仍在榜上榜 4 次（重入 3 次）累计约12小时52分 - 32Optimizing Ling-2.6-1T on TPU with SGLang-JAX: Hiding MoE Data Movement Behind Compute with One Pallas Kernel - LMSYS Org
Optimizing Ling-2.6-1T on TPU with SGLang-JAX: Hiding MoE Data Movement Behind Compute with One Pallas Kernel LMSYS Org
最高第 12 名00:03 达到00:03 首次观测上榜06:27 观测离榜上榜 5 次（重入 4 次）累计约4小时48分