HatforceSec says that after several days of custom kernel work, DeepSeek-V4.1-Flash runs on a 4xH200 machine at 653 tokens per second for a single user, scales to 64 concurrent users, and prefills at 42,000 tokens per second. It is in production at BugBunn...
VQV Signal
OPEN SOURCE
WATCH
TECHNICAL
BugBunny.ai open-sources kernels that run DeepSeek-V4.1-Flash fast on H200s
HatforceSec says that after several days of custom kernel work, DeepSeek-V4.1-Flash runs on a 4xH200 machine at 653 tokens per second for a single user, scales to 64 concurrent users, and prefills at 42,000 tokens per second. It is in production at BugBunn...
HatforceSec says that after several days of custom kernel work, DeepSeek-V4.1-Flash runs on a 4xH200 machine at 653 tokens per second for a single user, scales to 64 concurrent users, and prefills at 42,000 tokens per second. It is in production at BugBunny.ai, and the work is open source. Why it matters: Teams...
VQV organizes public signals from inspectable sources. It does not independently verify the underlying report.
Signal Strength 92%
Technical label WATCH
Public Interest 50
Category OPEN SOURCE
Reader Depth TECHNICAL
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
Public Interest components
Recognizable Entity Score 51
Practical Impact Score 38
Novelty Interest Score 94
Consequence Score 30
Curiosity Score 0
Shareability Score 63
VQV surfaced this signal because it is recent, relevant to AI Chips, connected to Scobleizer News Pulse (X).
No login, cookies, social SDKs, or automatic posting.