pinned
Build error
Agents
HeartMuLa
π
A Family of Open Sourced Music Foundation Models
gen
ginigini
AI & ML interests
None yet
Recent Activity
upvoted a collection 5 days ago
VKAE Accelerated upvoted an article 6 days ago
Adding a GPU Without Building One reacted to SeaWolf-AI's post with β€οΈ 6 days ago
π Adding a GPU without building one
AI is usually framed as "how smart is the model / how many GPUs did you buy." The real bottleneck is elsewhere β how efficiently you use the GPUs you already have.
Training happens once; inference runs the entire time users use your product. So a service's economics come down to cost per token. Inference acceleration uses software to pull several times more out of the same GPU β the effect of plugging in one more "virtual GPU."
VIDRAFT's VKAE, measured (B200, same-harness, no quality loss):
Qwen3.5-35B-A3B (MoE): 25.7 β 601 tok/s (23.4Γ)
Darwin-36B-Opus (in-house MoE): 25.0 β 280.8 (11.2Γ)
10,000+ tok/s peak aggregate under concurrency
The key: it's reproducible β model + serving shipped as one container.
docker pull vidraft/qwen35-vkae:601
Don't take our word for it β run it yourself. The mechanism will be released as a paper.
π Leaderboard & demo π https://huggingface.co/spaces/VIDraft/vkae
Articles π https://huggingface.co/blog/FINAL-Bench/vkae-leaderboardOrganizations
None yet