Inference at Full Throttle: LLM serving performance with vLLM, quantization, KV cache tuning and speculative decoding

Prix à partir de
9,19

En vedette

COMPARER TOUS LES MAGASINS EN LIGNE (2)

Description

Amazon Inference at Full Throttle: LLM serving performance with vLLM, quantization, KV cache tuning and speculative decoding

Comparer les boutiques en ligne (2)

Shop
Prix
Affranchissement
Prix total
9,19 
2,49 €
11,68 
Voir l’offre
2,49 € Shipping Costs
9,19 
2,49 €
11,68 
Voir l’offre
2,49 € Shipping Costs
Description (1)

Inference at Full Throttle: LLM serving performance with vLLM, quantization, KV cache tuning and speculative decoding


Spécifications du produit

Marque Independently Published
EAN
  • 9798192412626

Choix en vedette
9,19 
Voir l’offre