๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

Guitar Cat + LLM ใ€ŒWill @ SGLang Summit in SFใ€
@GenAI_is_real
๊ฐ€์ž… April 2024
0 ํŒ”๋กœ์ž‰ ์ค‘    0 ํŒฌ
More good news for Fish Audio Drama 3! ๐ŸŽ‰ Thanks to @_akhaliq for the INT4 quantization and his incredible support, SGLang Omni now officially supports Drama 3 INT4! The quantized checkpoint reduces engine weight memory from 37.0 GB to 20.8 GB, with comparable voice-cloning quality in our Seed-TTS EN evaluation. Making powerful speech models more accessible and affordable to serve is exactly what we love working on. We've also been working closely with the @huggingface team to expand our Drama 3 Space with a completely redesigned UI. Even more excitingly, the Space will soon run Drama 3 on SGLang Omni, powered by an H200 generously sponsored by Hugging Face! We're truly grateful for the recognition, trust, and support. Huge thanks again to AK, the Hugging Face team, and @FishAudio for making the model available with open weights. This is what a healthy open AI ecosystem looks like: model builders, inference engineers, and platform teams working together to make great models accessible to everyone. More optimizations coming soon! ๐Ÿš€ PR: Space:
๋” ๋ณด๊ธฐ