EmbeddedLLM (@embeddedllm) 's Twitter Profile
EmbeddedLLM

@embeddedllm

Your open-source AI ally. We specialize in integrating LLM into your business.

ID: 1716394660636295168

calendar_today23-10-2023 10:02:43

303 Tweet

621 Followers

1,1K Following

EmbeddedLLM (@embeddedllm) 's Twitter Profile Photo

vLLM 0.9.0 is HERE, unleashing HUGE performance on AMD GPUs! MI-Series: FP8 KV cache, +19.4% with AITER GEMM, +16.8% Qwen3 MoE (MI300X), +13.8% DeepSeek V3/R1! Consumer: πŸ“ˆ RX 9000 Series: +16.4% throughput πŸš€ RX 7000 Series: +19.0% performance gains AI at AMD AMD Radeon

vLLM 0.9.0 is HERE, unleashing HUGE performance on <a href="/AMD/">AMD</a> GPUs! 
MI-Series: FP8 KV cache, +19.4% with AITER GEMM, +16.8% Qwen3 MoE (MI300X), +13.8% DeepSeek V3/R1! 
Consumer: πŸ“ˆ RX 9000 Series: +16.4% throughput
πŸš€ RX 7000 Series: +19.0% performance gains
<a href="/AIatAMD/">AI at AMD</a> <a href="/AMDRadeon/">AMD Radeon</a>