Unverified50% confidenceFactExact time
The 3.11x is kernel-level forward acceleration, while 34% is end-to-end training step speed improvement; the two are measured on different bases.
1
Sources
50%
Confidence
Long-term
Relevance
10/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIf the optimizer itself is 1.5 times faster, in the case where the optimizer accounts for 10%, the end-to-end speedup is about 1/(0.9+0.1/1.5)≈1.03, that is, only about 3%.71% similarUnverifiedAfter restoring flushing, the Claude candidate achieved a completion speedup of 2.75× and a time-to-first-byte speedup of 2.80×, while Gemini achieved a completion speedup of 3.44× and a time-to-first-byte speedup of 3.54×, and GPT-5.4 achieved a completion speedup of 2.16× and a time-to-first-byte speedup of 2.19×.69% similarUnverifiedIn prime-rl, Qwen3 MoE training step speed improved by up to 34%.67% similarUnverifiedControlled measurements show that branch pruning brings a 1.426x speedup in step time.66% similarUnverifiedCompared to the interior-point solver IPOPT, the new solver achieves a median speedup of up to four times.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1112887API
curl https://kongchang.com/api/v1/knowledge/claims/1112887MCP
get_claim(id=1112887)