Hugging Face's logo
VIDRAFT_LAB's picture
🔄 In a Training Loop

VIDRAFT_LAB

SeaWolf-AI
113 27 220
Amiee7's profile picture ChBysk's profile picture yuch9933's profile picture
·
https://www.vidraft.net

AI & ML interests

Contact: arxivgpt@gmail.com

Recent Activity

reacted to theirpost with 😎 about 21 hours ago
We wrote up our run in The Fast Gemma Challenge — as vidraft-darwin — and wanted to share the recipe. 🙏 https://huggingface.co/spaces/gemma-challenge/gemma-dashboard Verified result: 510.58 TPS at PPL 2.3930 on a single A10G (fw188-ctk49-n64-patchbridge, re-run & VERIFIED). Honest note: on raw TPS there are faster runs (535+), but those went over the PPL bar and didn't verify — what we're proud of is the fastest result that keeps quality. The recipe is already open, so we explained each piece: sliding-window W188, CTK49 kernel tuning, noprecache (honest, verifiable measurement), and an N64 synthetic warmup bridge that shrinks the public↔private gap (~15 TPS), plus INT4 + MTP K=7 + CUDA-graph capture. One rule: only stack quality-neutral speedups. Huge thanks to @firfir-cast, @gemma-slayer, @chiku-inu, @kenyan-duma, @dixie-flatline and everyone who shared their experiments. Full write-up 👇 https://huggingface.co/blog/FINAL-Bench/fast-gemma
reacted to theirpost with 🧠 about 21 hours ago
We wrote up our run in The Fast Gemma Challenge — as vidraft-darwin — and wanted to share the recipe. 🙏 https://huggingface.co/spaces/gemma-challenge/gemma-dashboard Verified result: 510.58 TPS at PPL 2.3930 on a single A10G (fw188-ctk49-n64-patchbridge, re-run & VERIFIED). Honest note: on raw TPS there are faster runs (535+), but those went over the PPL bar and didn't verify — what we're proud of is the fastest result that keeps quality. The recipe is already open, so we explained each piece: sliding-window W188, CTK49 kernel tuning, noprecache (honest, verifiable measurement), and an N64 synthetic warmup bridge that shrinks the public↔private gap (~15 TPS), plus INT4 + MTP K=7 + CUDA-graph capture. One rule: only stack quality-neutral speedups. Huge thanks to @firfir-cast, @gemma-slayer, @chiku-inu, @kenyan-duma, @dixie-flatline and everyone who shared their experiments. Full write-up 👇 https://huggingface.co/blog/FINAL-Bench/fast-gemma
reacted to theirpost with 👍 about 21 hours ago
We wrote up our run in The Fast Gemma Challenge — as vidraft-darwin — and wanted to share the recipe. 🙏 https://huggingface.co/spaces/gemma-challenge/gemma-dashboard Verified result: 510.58 TPS at PPL 2.3930 on a single A10G (fw188-ctk49-n64-patchbridge, re-run & VERIFIED). Honest note: on raw TPS there are faster runs (535+), but those went over the PPL bar and didn't verify — what we're proud of is the fastest result that keeps quality. The recipe is already open, so we explained each piece: sliding-window W188, CTK49 kernel tuning, noprecache (honest, verifiable measurement), and an N64 synthetic warmup bridge that shrinks the public↔private gap (~15 TPS), plus INT4 + MTP K=7 + CUDA-graph capture. One rule: only stack quality-neutral speedups. Huge thanks to @firfir-cast, @gemma-slayer, @chiku-inu, @kenyan-duma, @dixie-flatline and everyone who shared their experiments. Full write-up 👇 https://huggingface.co/blog/FINAL-Bench/fast-gemma
View all activity

Organizations

FINAL_Bench's profile picture Gemma Challenge's profile picture PPALLI's profile picture