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

Dipika Sikka ๐Ÿ
@dsikka84
MLE @RedHat_AI @neuralmagic I work on LLM Compressor & Speculators
๊ฐ€์ž… March 2026
17 ํŒ”๋กœ์ž‰ ์ค‘    157 ํŒฌ
@RedHat_AI Some performance plots to demonstrate this, illustrating per-user interactivity combining our Quantized NVFP4 model with our trained DSpark speculator