Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,13 @@ Trusted by Operators of Trillion Dollar Token Factories such as OpenAI, Meta, Mi

## News

- **[2026/11]** 🔥 Kimi K3.1 Pro: continuous benchmarks live since Day 0 on B200, B300, GB200 and MI355X (SGLang + vLLM)
- **[2026/11]** 🔥 PowerX: measured power is now collected by default on multi-node runs, including NVL72 Grace CPU, per-host GPU and AMD EPYC CPU package power
- **[2026/11]** GLM-5.3-Flash: added AgentX benchmarks on GB200 (FP8 + NVFP4), MI300X and MI325X with HiCache [dashboard](https://inferencex.semianalysis.com/agentx)
- **[2026/10]** MiniMax M3.1 Flash: Day 0 AgentX benchmarks with DSpark speculative decoding on B200 and B300 [dashboard](https://inferencex.semianalysis.com/agentx)
- **[2026/10]** Muse Spark Open: added AgentX benchmarks on B300 and GB300 (SGLang) [dashboard](https://inferencex.semianalysis.com/agentx)
- **[2026/10]** Open-source power model (beta) for estimating system power from measured GPU, CPU and memory telemetry
- **[2026/09]** Vera Rubin NVL72, TPUv7x Ironwood and RTX PRO 6000 Server are now officially supported
- **[2026/09]** DeepSeek V4.1 Flash: added AgentX benchmarks [dashboard](https://inferencex.semianalysis.com/agentx)
- **[2026/08]** Qwen3.8-Flash-Next: added AgentX benchmarks with native multi-token prediction (MTP) [dashboard](https://inferencex.semianalysis.com/agentx)
- **[2026/08]** 🔥 **AgentX: World's First Fully Open Source Apache 2.0 Realistic 1Mil+ Long Context, Multi Turn Benchmark Live** [dashboard](https://inferencex.semianalysis.com/agentx)
Expand Down
7 changes: 7 additions & 0 deletions README_zh.md
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,13 @@

## 新闻

- **[2026/11]** 🔥 Kimi K3.1 Pro:自 Day 0 起持续基准测试上线,覆盖 B200、B300、GB200 与 MI355X(SGLang + vLLM)
- **[2026/11]** 🔥 PowerX:多节点运行默认采集实测功耗,包括 NVL72 Grace CPU、逐主机 GPU 与 AMD EPYC CPU 封装功耗
- **[2026/11]** GLM-5.3-Flash:新增 GB200(FP8 + NVFP4)、MI300X 与 MI325X(含 HiCache)上的 AgentX 基准测试 [仪表盘](https://inferencex.semianalysis.com/agentx)
- **[2026/10]** MiniMax M3.1 Flash:在 B200 与 B300 上提供使用 DSpark 投机解码的 Day 0 AgentX 基准测试 [仪表盘](https://inferencex.semianalysis.com/agentx)
- **[2026/10]** Muse Spark Open:新增 B300 与 GB300(SGLang)上的 AgentX 基准测试 [仪表盘](https://inferencex.semianalysis.com/agentx)
- **[2026/10]** 开源功耗模型(Beta):基于实测 GPU、CPU 与内存遥测估算系统功耗
- **[2026/09]** Vera Rubin NVL72、TPUv7x Ironwood 与 RTX PRO 6000 Server 现已获得官方支持
- **[2026/09]** DeepSeek V4.1 Flash:新增 AgentX 基准测试 [仪表盘](https://inferencex.semianalysis.com/agentx)
- **[2026/08]** Qwen3.8-Flash-Next:新增使用原生多 Token 预测(MTP)的 AgentX 基准测试 [仪表盘](https://inferencex.semianalysis.com/agentx)
- **[2026/08]** 🔥 **AgentX:全球首个完全开源、采用 Apache 2.0 许可的真实百万级长上下文多轮基准测试上线** [仪表盘](https://inferencex.semianalysis.com/agentx)
Expand Down
Loading