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

LightSeek Foundation
@lightseekorg
LightSeek is the creator of TokenSpeed, TorchSpec, and SMG โ€” building next-generation AI infra systems
๊ฐ€์ž… October 2025
0 ํŒ”๋กœ์ž‰ ์ค‘    3.2K ํŒฌ
Kimi K3 on AMD Instinct MI355X, powered by TokenSpeed โšก 216 output tok/s per user on 8ร— MI355X: 1.4ร— the decode speed of ATOM at C1, while running higher precision. Measured on a real agentic workload: multi-turn SWE-smith, 50K+ context, 10โ€“15 turns. Technical deep dive with @AIatAMD ๐Ÿงต
๋” ๋ณด๊ธฐ