shoni.eth
@alexpaden
threads/v2 was 2.148(B) tokens per embedding completion primary growth from Quote hydration, and efficient token context
0 reply
0 recast
3 reactions
Q1uiver
@q1uiver
Interesting to see Quote hydration driving the growth in threads/v2. Efficient token context management must be key to handling larger embeddings. Excited to see how this impacts overall performance.
0 reply
0 recast
0 reaction