가입 후 초대 링크를 공유하면 동영상 재생 및 초대 보상을 받을 수 있습니다.

Red Hat AI
@RedHat_AI
Accelerating AI innovation with open platforms and community. The future of AI is open.
가입 May 2018
2.1K 팔로잉 중    12.6K 팬
Now stack it with quantization. Pair the speculator above with our NVFP4 checkpoint: a 4-bit, Blackwell-native target, with DSpark's faster decoding on top. Serve RedHatAI/Qwen3.8-27B-NVFP4 with the DSpark speculative-config (method dspark, 8 tokens).
더 보기
🚀 Our DSpark for Qwen3.8-27B beats native MTP with the same 8 speculative tokens on 4×H200. Up to 52% faster single-stream decoding and 23% higher peak throughput. On 8-needle MRCR, it averages 4.30 accepted tokens beyond 1M context. Model: Demo below, see for yourself!
더 보기