你可能会喜欢
Awesome!!!
Don’t let your memes be dreams kids. Look where they can take you.
Happy 4th July! Speed is the Moat & @AnushElangovan & his team Keeps Running Faster & Faster. Still lots of areas where ROCm has gaps but many are already closing
Practicing the Lil Yachty entrance for the SGLang meetup to look like x.com/SemiAnalysis_/… but I think I am going to ask @dylan522p to make that entrance. Either way come meet our engineering teams, talk shop, get some swag GPUs and hang at the SGLang meetup…
AMD is helping foster its neocloud ecosystem by enabling all key partners to build clusters with at least 1,000 MI355X GPUs each. AMD is offering a range of financial incentives including renting back a large portion of the GPUs for internal R&D, go-to-market partnerships, and…
.@vllm_project V1 is now fully optimized for AMD Instinct™ MI300X GPUs?! 🚀🚀🚀 This major architectural upgrade to the popular LLM inference engine brings significant performance gains to AMD hardware. Dive into the details in the thread below...
It's a new era for LLM Inference Performance! Check out this blog to explore key improvements introduced in vLLM V1 for AMD GPUs, as well as the main benefits users can expect from migrating to this new version. 🔗 bit.ly/44QhTc6
Really excited to welcome the Brium team to AMD to supercharge our software efforts. Let's go. amd.com/en/blogs/2025/…
* Great to see our products do well (MI300 vs H100; MI325 vs H200) and deliver compelling alternatives to the market. * Continuing to expand neocloud offerings with AMD. * We continue to advance our SW. Expanding dev compute and community CI is a priority. More sglang CI and…
Day 0 support for llm-d on AMD Instinct!!! Kudo to the team. rocm.blogs.amd.com/artificial-int…
Great blog, and great collaboration with @Microsoft . Awesome DeepSeek performance on AMD MI300X, kudo to the team!!! @AMD techcommunity.microsoft.com/blog/machinele…
Exciting news for AI developers! AMD is thrilled to announce Day 0 support for Meta's groundbreaking Llama 4 multimodal models on our AMD Instinct™ MI300X and MI325X GPUs. rocm.blogs.amd.com/artificial-int…
AMD updated Docker images incorporate torchtune finetuning, FP8 support, single node performance boost, bug fixes rocm.blogs.amd.com/artificial-int…
Join me in supporting a nonprofit through Charity Navigator's Giving Basket, an easy and secure way to donate to multiple charities in one convenient checkout. charitynavigator.org/index.cfm?bay=… #lafires #Donate
Exciting news from AMD! The new DeepSeek-V3 model from DeepSeek is now integrated on AMD Instinct™ GPUs, enhancing performance with SGLang optimization. To learn more amd.com/en/developer/r…
AMD Nitro Diffusion: One-Step Text-to-Image Generation Models To learn more about it amd.com/en/developer/r…
United States 趋势
- 1. phil 80.8K posts
- 2. phan 76.2K posts
- 3. Columbus 222K posts
- 4. President Trump 1.26M posts
- 5. Kincaid 1,567 posts
- 6. Falcons 13.5K posts
- 7. Doug Eddings N/A
- 8. Middle East 322K posts
- 9. Springer 11.1K posts
- 10. Gilbert 9,687 posts
- 11. Martin Sheen 1,483 posts
- 12. Mike McCoy N/A
- 13. Yesavage 3,316 posts
- 14. Monday Night Football 6,747 posts
- 15. Thanksgiving 60.9K posts
- 16. Go Bills 7,030 posts
- 17. Ray Ray 95.4K posts
- 18. Bijan 3,134 posts
- 19. Knox 3,122 posts
- 20. John Oliver 9,235 posts
Something went wrong.
Something went wrong.