#MLperf - Twitter Hashtag

3 days ago

MLCommons adds native S3 support to MLPerf Storage v3.0, validating object storage performance for demanding AI workloads. #objectstorage #s3 #mlperf #cloudinfrastructure

0

9

BigDATAWire @BigDATAwireNews

6 days ago

Everpure Leads MLPerf Storage Tests for Large-Model Checkpointing and KV Cache @EverpureData #MLPerf #BigDATAwire https://t.co/7k0fKX0Ejn

0

1

0

174

HPCwire @HPCwire

6 days ago

Everpure Leads MLPerf Storage Tests for Large-Model Checkpointing and KV Cache @EverpureData #MLPerf #HPC https://t.co/WQcNcNE8xz

0

2

0

432

TuringData @TuringData_IO

7 days ago

Proudly, TuringData ranked #2 in 3D U-Net training throughput, while also showing strong performance across checkpointing and KV cache workloads. Thank you, @MLCommons, for establishing such an open and rigorous benchmark! #MLPerf

MLCommons @MLCommons

7 days ago

MLPerf Storage v3.0 is out. 144 results. 19 orgs. 11 first-time submitters. 4 workloads: training, checkpointing, vector DB, KV cache. New efficiency metrics: rack-unit density and provisioned power. S3 API support. 8B to 1250B parameter checkpointing. https://t.co/yEiumHDd8d

MLCommons's tweet photo. MLPerf Storage v3.0 is out.

144 results. 19 orgs. 11 first-time submitters.

4 workloads: training, checkpointing, vector DB, KV cache.
New efficiency metrics: rack-unit density and provisioned power.
S3 API support. 8B to 1250B parameter checkpointing.
https://t.co/yEiumHDd8d https://t.co/khvqJlPXW0

2

11

3

2

781

0

20

Nebius

@nebiusai

7 days ago

New MLPerf® Storage v3.0 results are in! Nebius Object Storage fed 768 simulated B200 accelerators on RetinaNet, the highest accelerator count of any submission in this round. Get the full breakdown: https://t.co/eMtDqIEzHg #MLPerf #AI #ObjectStorage

nebiusai's tweet photo. New MLPerf® Storage v3.0 results are in! Nebius Object Storage fed 768 simulated B200 accelerators on RetinaNet, the highest accelerator count of any submission in this round.

Get the full breakdown: https://t.co/eMtDqIEzHg

#MLPerf #AI #ObjectStorage https://t.co/nz5ZqLwEln

1

90

6

2

10K

David Kanter

@TheKanter

28 days ago

Congrats to Infinity and D-Matrix, can’t wait to see the #MLPerf results :)

Jeremy Nixon - Automating AI Research

@JvNixon

28 days ago

Every chip. Every model. Lightning speed. https://t.co/Rogvbu8zBC

18

88

16

47

68K

1

5

0

1

873

MLCommons @MLCommons

about 1 month ago

LIVE NOW @NYSE : @TheKanter is on @theCUBE @NYSEWired talking AI inference benchmarks, MLPerf Endpoints v0.7 - a new way to measure GenAI service performance in real-world deployments. Tune in: https://t.co/UVtWZersXo #MLPerf #AIInference #NYSEWired

MLCommons's tweet photo. LIVE NOW @NYSE : @TheKanter is on @theCUBE @NYSEWired talking AI inference benchmarks, MLPerf Endpoints v0.7 - a new way to measure GenAI service performance in real-world deployments.

Tune in: https://t.co/UVtWZersXo
#MLPerf #AIInference #NYSEWired https://t.co/uGHJ2s7iDk

1

4

1

0

273

Principled Tech @PrincipledTech

about 2 months ago

AI leaders need infrastructure built both for today’s workloads and tomorrow’s growth. Published MLPerf results suggest @AMD Instinct MI355X GPUs are well positioned for both. Get the facts: https://t.co/ecjLqZIh3M #MLPerf #Instinct #AI

PrincipledTech's tweet photo. AI leaders need infrastructure built both for today’s workloads and tomorrow’s growth. Published MLPerf results suggest @AMD Instinct MI355X GPUs are well positioned for both. Get the facts: https://t.co/ecjLqZIh3M
#MLPerf #Instinct #AI https://t.co/cC2XSIUrAs

0

2

0

44

David Kanter

@TheKanter

2 months ago

Thrilled to see the team leading #MLPerf into the agentic era

MLCommons @MLCommons

2 months ago

MLPerf Inference now measures multi-turn agents. 990 trajectories, Kimi K2.6 + Qwen3.6-35B-A3B, Pareto-curve performance, three-level accuracy. Built on MLPerf Endpoints. https://t.co/CplssZ45hM MLPerf #AgenticAI #LLM #Inference #Kimi #Qwen #MLCommons

MLCommons's tweet photo. MLPerf Inference now measures multi-turn agents.

990 trajectories, Kimi K2.6 + Qwen3.6-35B-A3B, Pareto-curve performance, three-level accuracy.
Built on MLPerf Endpoints.
https://t.co/CplssZ45hM

MLPerf #AgenticAI #LLM #Inference #Kimi #Qwen #MLCommons https://t.co/Yab0cHx9p5

1

12

1

0

242K

0

3

0

751

David Kanter

@TheKanter

2 months ago

Excited to work with the whole team at Gimlet on #MLPerf!

Gimlet Labs

@gimletlabs

2 months ago

Gimlet is now a member organization of @MLCommons, collaborating with other experts to create new @MLPerf benchmarks for agentic inference. As David Patterson observed back in 2012: "When a field has good benchmarks, we settle debates and the field makes rapid progress." As agents become the dominant software workload, open, standard benchmarks will be crucial to the industry-wide work in driving better performance and efficiency. Blog post: https://t.co/dNAnCkJUdZ

0

14

2

0

2K

1

7

1

0

1K

Netweb Technologies India Ltd. @netwebtech

4 months ago

Netweb Technologies’s first submission to MLPerf Inference by MLCommons marks a key step in its AI journey. Benchmarks measure performance—not narratives. As AI scales, inference defines real-world impact. India is building, not just consuming, AI #MLPerf @nvidia

netwebtech's tweet photo. Netweb Technologies’s first submission to MLPerf Inference by MLCommons marks a key step in its AI journey.
Benchmarks measure performance—not narratives. As AI scales, inference defines real-world impact. India is building, not just consuming, AI
#MLPerf @nvidia https://t.co/U60Gh1HKZT

0

14

2

0

434

MiTAC Computing @MiTACcomputing

5 months ago

Proud to be part of @AMD MLPerf Inference 6.0 milestone 🚀 Powered by AMD Instinct MI355X, enabling scalable AI inference from single-node to multi-node. #AI #MLPerf #AMD #GPU #Inference

AMD

@AMD

5 months ago

New workloads. New scale. New proof points. With AMD Instinct MI355X GPUs, we delivered breakthrough MLPerf Inference 6.0 results, including 1M+ tokens/sec at multi-node scale and first-time submissions on GPT-OSS-120B and Wan-2.2. Read the full story here: https://t.co/2vCKAwWab9

AMD's tweet photo. New workloads. New scale. New proof points. With AMD Instinct MI355X GPUs, we delivered breakthrough MLPerf Inference 6.0 results, including 1M+ tokens/sec at multi-node scale and first-time submissions on GPT-OSS-120B and Wan-2.2.

Read the full story here: https://t.co/2vCKAwWab9

13

194

33

10

25K

0

3

1

0

87

MLCommons @MLCommons

5 months ago

MLPerf Client v1.6 is out - runtime updates for Windows ML, llama.cpp, and Apple MLX, plus GUI improvements for faster, smoother benchmarking on Windows, Mac, and iPad. https://t.co/Z2dVBiToAq #MLPerf #AIBenchmarking

MLCommons's tweet photo. MLPerf Client v1.6 is out - runtime updates for Windows ML, llama.cpp, and Apple MLX, plus GUI improvements for faster, smoother benchmarking on Windows, Mac, and iPad.
https://t.co/Z2dVBiToAq

#MLPerf #AIBenchmarking https://t.co/updGzaJy50

0

5

2

0

1K

HPCwire @HPCwire

5 months ago

AMD MLPerf Submission Highlights MI355X Gains, Multinode Inference Performance @AMD #AMD #MLPerf #HPC https://t.co/ovdtSeRhBf

0

6

3

0

351

Juicedata

@JuicedataInc

5 months ago

🛠️ Linaro (an #Arm ecosystem org) tuned #JuiceFS on Arm with #MLPerf. ✅ Workloads: 3D U‑Net, ResNet‑50, CosmoFlow ✅ Single & two nodes ✅ Bottlenecks: memory copy, metadata, cross‑socket ✅ Fixes: CPU pinning, NUMA grouping, cache tuning 👇Learn more https://t.co/Yz1MEcTbyi

0

3

0

870

Supermicro Japan【公式】 @SupermicroJapan

5 months ago

🚀 MLPerf Inferenceでトップタイムを記録！ LLM、リーズニングLLM、生成AI、レコメンデーション、テキスト、GNNなど、10種類のAI推論パフォーマンスでリーダーシップを発揮💡 次世代AIインフラを支えるSupermicroの実力👇 https://t.co/LU7mMIpP7f #AI #MLPerf #Supermicro #GPU

5

2

0

160

MLCommons @MLCommons

5 months ago

Want to explore the MLPerf Inference v6.0 results yourself? Dive into our interactive dashboard - filter by benchmark, system, and scenario to see how the latest hardware stacks up. 📊 🔗 https://t.co/igTFQiZI0n #MLPerf #MLCommons #AI #inference

0

3

2

0

252

QCT @QuantaQCT

5 months ago

.@QuantaQCT delivered strong results in #MLPerf Inference v6.0 with #QuantaGrid AI servers powered by NVIDIA Blackwell and Blackwell Ultra GPUs, covering key inference workloads across vision, speech, language, and recommendations. Read blog: https://t.co/NkL2igMTtb

QuantaQCT's tweet photo. .@QuantaQCT delivered strong results in #MLPerf Inference v6.0 with #QuantaGrid AI servers powered by NVIDIA Blackwell and Blackwell Ultra GPUs, covering key inference workloads across vision, speech, language, and recommendations.
Read blog: https://t.co/NkL2igMTtb https://t.co/f2nGQgORVI

0

8

1

0

829

Lambda @LambdaAPI

5 months ago

Lambda's @mlcommons #MLPerf Inference v6.0 results are out. Three findings worth knowing before your next deployment: https://t.co/1wSR3AVGaV

LambdaAPI's tweet photo. Lambda's @mlcommons #MLPerf Inference v6.0 results are out. Three findings worth knowing before your next deployment: https://t.co/1wSR3AVGaV https://t.co/ealSEejhsi

1

25

5

1

3K

MLCommons @MLCommons

5 months ago

MLPerf Inference v6.0 is here - our most significant benchmark update ever. 5 new/updated benchmarks. 24 submitting organizations. Industry-first tests for text-to-video and speculative decoding. Full results: https://t.co/avj9D2onVG #MLPerf #MLCommons

MLCommons's tweet photo. MLPerf Inference v6.0 is here - our most significant benchmark update ever.
5 new/updated benchmarks. 24 submitting organizations. Industry-first tests for text-to-video and speculative decoding.
Full results: https://t.co/avj9D2onVG
#MLPerf #MLCommons https://t.co/E92R426NNy

2

12

4

3

4K

Top Tweets for #MLperf

Last Seen Hashtags on Sotwe

Trends for you

Most Popular Users