Ornith(@ornith_):🔍We dove a bit deeper and analyzed how multi-token prediction (MTP) works in Ornith 1.5 models. 🪽With MTP, Ornith 1.5 gain inference speedups without quality loss via self-speculative decoding: models use their own MTP head to draft tokens and verify them in a forward pass. 🐦MTP weights are now updated for all 9B, 35B, and 397B models in BF16, GGUF, FP8, and NVFP4 variants (except 397B NVFP4, will be updated today).

Ornith

@ornith_

Once you have tasted flight, you will walk the earth with your eyes turned skywards.

가입 June 2026

308 팔로잉 중 18.9K 팬

Ornith@ornith_

2026.08.26 18:26

🔍We dove a bit deeper and analyzed how multi-token prediction (MTP) works in Ornith 1.5 models. 🪽With MTP, Ornith 1.5 gain inference speedups without quality loss via self-speculative decoding: models use their own MTP head to draft tokens and verify them in a forward pass. 🐦MTP weights are now updated for all 9B, 35B, and 397B models in BF16, GGUF, FP8, and NVFP4 variants (except 397B NVFP4, will be updated today).