HyperAI

**Contents at a glance:**TVMCon 2023 is finally here! For this year's conference, we have invited special guests to explain the future development plan of Apache TVM online~

**Keywords:**TVM Chinese Community TVMCon 2023

**The annual TVMCon opened at midnight on March 16th, Beijing time.**The three-day event covers the most noteworthy technical advances and application cases of deep learning compilation and optimization this year, from tutorials, keynotes, best practices to lightning talks.

This year's conference will still be held online. In order to further discuss TVM's future development plans and provide more detailed insights for the docking of enterprise software and hardware ecosystems,**HyperAI specially invited Apache TVM PMC and Shanghai Jiaotong University Ph.D. Feng Siyuan,**We will interpret the TVM Community Keynote online. You are welcome to participate and discuss online~

⏰ Event time:

March 18, 10:30-11:30 Beijing time (this Saturday)

🙌🏻 Participation method: Tencent Meeting

* Click the link to join:

https://meeting.tencent.com/dm/R6ALPSQXQFbB

* Or enter the meeting number:

182-282-759

Join the online discussion this Saturday from 10:30-11:30 a.m.Learn about the development direction of Apache TVM and make smarter decisions for business applications compiled with machine learning!

Related Links:

[1] TVM Chinese documentation:

https://tvm.hyper.ai/

[2] TVMCon 2023 online conference:

https://www.tvmcon.org/

Live Broadcast | Let’s Talk About This Year’s TVM Community Keynote

Related News

Tencent open-sources Hy-MT1.5 Translation Model: 440MB Achieves top-tier Translation Capabilities; MIT Jointly Releases MathNet: a Multimodal Mathematical Inference Benchmark Covering 27,000 Real Olympiad Math problems.

Anima V1, a brand-new Raw Image Model, Has Been Released, Focusing on anime-style Image Generation; the MemLens Multimodal long-range Memory Evaluation Dataset Covers cross-conversation text-to-image Reasoning and Knowledge Update mechanisms.

MiniCPM5-1B, Trained Using RL+OPD, Achieves state-of-the-art (SOTA) Performance on Multiple Complex Tasks; the CHI-Bench Dataset for Evaluating Medical Agents, Designed for Automation of Complex Healthcare Processes, Has Been released.

Supports live-action/animation/animal-driven Video Generation; Meituan's open-source multi-style audio-driven Video Generation Framework LongCat 1.5 Enhances VLM's Chart Reconstruction and Table Extraction Capabilities Using the million-level Chart Understanding Dataset ChartNet.

4-step Image output/4K quality/6x Speedup, PiD Uses Pixel Diffusion to Unify Decoding and super-resolution Output; SA-3DAO: a Dataset Containing 1000 Pairs of Real Images Paired With Handcrafted 3D Meshes by artists.

Event Preview | AI Computing, TileRT, Tencent, Huawei, and AI Computing Innovation Join Forces to Explore Multi-Level Collaborative Optimization

Can Emojis Control Speech Generation? Irodori-TTS Is a Japanese TTS Based on the RF-DiT Architecture; Eczema and Tinea Skin Disease Datasets: Supporting Medical Image Classification and Transfer learning.

Technical Salon | Zhiyuan, TileRT, Tencent, Huawei, and Zhiyuan Innovation Gather in Beijing to Focus on AI Compilation multi-level Optimization practices.

ICML 26 Outstanding Papers: Tsinghua JustGRPO Overcomes the dLLM Inference Bottleneck; Say Goodbye to Simple Instruction Tests: Agents Last Exam Comprehensively Evaluates the long-range Professional Capabilities of Intelligent agents.

Early Bird Tickets Countdown! The AI Compiler Technology Salon in Beijing Is Coming!

One Day to Go! Zhiyuan, TileRT, Tencent, Huawei, and Zhiyuan Innovation Gather to Explore multi-level Collaborative Optimization of AI compilation.

Chen Tianqi: In the Agent Era, How Should We Rethink AI Compilers?

Related News

Tencent open-sources Hy-MT1.5 Translation Model: 440MB Achieves top-tier Translation Capabilities; MIT Jointly Releases MathNet: a Multimodal Mathematical Inference Benchmark Covering 27,000 Real Olympiad Math problems.

Anima V1, a brand-new Raw Image Model, Has Been Released, Focusing on anime-style Image Generation; the MemLens Multimodal long-range Memory Evaluation Dataset Covers cross-conversation text-to-image Reasoning and Knowledge Update mechanisms.

MiniCPM5-1B, Trained Using RL+OPD, Achieves state-of-the-art (SOTA) Performance on Multiple Complex Tasks; the CHI-Bench Dataset for Evaluating Medical Agents, Designed for Automation of Complex Healthcare Processes, Has Been released.

Supports live-action/animation/animal-driven Video Generation; Meituan's open-source multi-style audio-driven Video Generation Framework LongCat 1.5 Enhances VLM's Chart Reconstruction and Table Extraction Capabilities Using the million-level Chart Understanding Dataset ChartNet.

4-step Image output/4K quality/6x Speedup, PiD Uses Pixel Diffusion to Unify Decoding and super-resolution Output; SA-3DAO: a Dataset Containing 1000 Pairs of Real Images Paired With Handcrafted 3D Meshes by artists.

Event Preview | AI Computing, TileRT, Tencent, Huawei, and AI Computing Innovation Join Forces to Explore Multi-Level Collaborative Optimization

Can Emojis Control Speech Generation? Irodori-TTS Is a Japanese TTS Based on the RF-DiT Architecture; Eczema and Tinea Skin Disease Datasets: Supporting Medical Image Classification and Transfer learning.

Technical Salon | Zhiyuan, TileRT, Tencent, Huawei, and Zhiyuan Innovation Gather in Beijing to Focus on AI Compilation multi-level Optimization practices.

ICML 26 Outstanding Papers: Tsinghua JustGRPO Overcomes the dLLM Inference Bottleneck; Say Goodbye to Simple Instruction Tests: Agents Last Exam Comprehensively Evaluates the long-range Professional Capabilities of Intelligent agents.

Early Bird Tickets Countdown! The AI Compiler Technology Salon in Beijing Is Coming!

One Day to Go! Zhiyuan, TileRT, Tencent, Huawei, and Zhiyuan Innovation Gather to Explore multi-level Collaborative Optimization of AI compilation.

Chen Tianqi: In the Agent Era, How Should We Rethink AI Compilers?

Command Palette

Live Broadcast | Let’s Talk About This Year’s TVM Community Keynote

Related News

Tencent open-sources Hy-MT1.5 Translation Model: 440MB Achieves top-tier Translation Capabilities; MIT Jointly Releases MathNet: a Multimodal Mathematical Inference Benchmark Covering 27,000 Real Olympiad Math problems.

Anima V1, a brand-new Raw Image Model, Has Been Released, Focusing on anime-style Image Generation; the MemLens Multimodal long-range Memory Evaluation Dataset Covers cross-conversation text-to-image Reasoning and Knowledge Update mechanisms.

MiniCPM5-1B, Trained Using RL+OPD, Achieves state-of-the-art (SOTA) Performance on Multiple Complex Tasks; the CHI-Bench Dataset for Evaluating Medical Agents, Designed for Automation of Complex Healthcare Processes, Has Been released.

Supports live-action/animation/animal-driven Video Generation; Meituan's open-source multi-style audio-driven Video Generation Framework LongCat 1.5 Enhances VLM's Chart Reconstruction and Table Extraction Capabilities Using the million-level Chart Understanding Dataset ChartNet.

4-step Image output/4K quality/6x Speedup, PiD Uses Pixel Diffusion to Unify Decoding and super-resolution Output; SA-3DAO: a Dataset Containing 1000 Pairs of Real Images Paired With Handcrafted 3D Meshes by artists.

Event Preview | AI Computing, TileRT, Tencent, Huawei, and AI Computing Innovation Join Forces to Explore Multi-Level Collaborative Optimization

Can Emojis Control Speech Generation? Irodori-TTS Is a Japanese TTS Based on the RF-DiT Architecture; Eczema and Tinea Skin Disease Datasets: Supporting Medical Image Classification and Transfer learning.

Technical Salon | Zhiyuan, TileRT, Tencent, Huawei, and Zhiyuan Innovation Gather in Beijing to Focus on AI Compilation multi-level Optimization practices.

ICML 26 Outstanding Papers: Tsinghua JustGRPO Overcomes the dLLM Inference Bottleneck; Say Goodbye to Simple Instruction Tests: Agents Last Exam Comprehensively Evaluates the long-range Professional Capabilities of Intelligent agents.

Early Bird Tickets Countdown! The AI Compiler Technology Salon in Beijing Is Coming!

One Day to Go! Zhiyuan, TileRT, Tencent, Huawei, and Zhiyuan Innovation Gather to Explore multi-level Collaborative Optimization of AI compilation.

Chen Tianqi: In the Agent Era, How Should We Rethink AI Compilers?

Related News

Tencent open-sources Hy-MT1.5 Translation Model: 440MB Achieves top-tier Translation Capabilities; MIT Jointly Releases MathNet: a Multimodal Mathematical Inference Benchmark Covering 27,000 Real Olympiad Math problems.

Anima V1, a brand-new Raw Image Model, Has Been Released, Focusing on anime-style Image Generation; the MemLens Multimodal long-range Memory Evaluation Dataset Covers cross-conversation text-to-image Reasoning and Knowledge Update mechanisms.

MiniCPM5-1B, Trained Using RL+OPD, Achieves state-of-the-art (SOTA) Performance on Multiple Complex Tasks; the CHI-Bench Dataset for Evaluating Medical Agents, Designed for Automation of Complex Healthcare Processes, Has Been released.

Supports live-action/animation/animal-driven Video Generation; Meituan's open-source multi-style audio-driven Video Generation Framework LongCat 1.5 Enhances VLM's Chart Reconstruction and Table Extraction Capabilities Using the million-level Chart Understanding Dataset ChartNet.

4-step Image output/4K quality/6x Speedup, PiD Uses Pixel Diffusion to Unify Decoding and super-resolution Output; SA-3DAO: a Dataset Containing 1000 Pairs of Real Images Paired With Handcrafted 3D Meshes by artists.

Event Preview | AI Computing, TileRT, Tencent, Huawei, and AI Computing Innovation Join Forces to Explore Multi-Level Collaborative Optimization

Can Emojis Control Speech Generation? Irodori-TTS Is a Japanese TTS Based on the RF-DiT Architecture; Eczema and Tinea Skin Disease Datasets: Supporting Medical Image Classification and Transfer learning.

Technical Salon | Zhiyuan, TileRT, Tencent, Huawei, and Zhiyuan Innovation Gather in Beijing to Focus on AI Compilation multi-level Optimization practices.

ICML 26 Outstanding Papers: Tsinghua JustGRPO Overcomes the dLLM Inference Bottleneck; Say Goodbye to Simple Instruction Tests: Agents Last Exam Comprehensively Evaluates the long-range Professional Capabilities of Intelligent agents.

Early Bird Tickets Countdown! The AI Compiler Technology Salon in Beijing Is Coming!

One Day to Go! Zhiyuan, TileRT, Tencent, Huawei, and Zhiyuan Innovation Gather to Explore multi-level Collaborative Optimization of AI compilation.

Chen Tianqi: In the Agent Era, How Should We Rethink AI Compilers?