O caso de uso: como Wadhwani AI implanta TrueFoundry
Wadhwani AI, a non-profit, runs its Vachan Samiksha oral reading fluency model, which needs GPUs for inference, on TrueFoundry deployed on its own Kubernetes infrastructure instead of its cloud provider's managed ML service. The team uses it for deployment, queue-based GPU autoscaling, scheduled scaling and spot instances to serve pilots in schools.
Outros resultados informados
Números publicados no estudo de caso de TrueFoundry. Eles não são medidos de forma independente pelo usedby.
Scale the application to handle 10X Requests per second compared to the managed ML Service.
Reduce the latency of requests by ~80% when the pods are scaling horizontally.
We realized that TrueFoundry could scale up 78% faster than managed ML service, which gave the user much faster responses.
The end-to-end time taken to respond to the query was 40% less with TrueFoundry.
Nas palavras do cliente
For me the biggest differentiator working with TrueFoundry was the ease of usage and the quick response and support provided by the team. I was able to setup and migrate our entire code base in less than 1 day which was amazing. During the pilot and whenever we had any doubts or request the TrueFoundry team was available immediately to solve our doubts and support us. Besides these factors we are getting a massive cost reduction which is super helpful for the project.Outras empresas que usam TrueFoundry
Clientes de todos os setores, com evidências públicas.
Adopt AIConfirmado
Aviso AIConfirmado
Aviva CreditoConfirmado
ExamRoom.AIConfirmado
FloQastConfirmado
Games24x7ConfirmadoIr direto à fonte
Com base no estudo de caso publicado por TrueFoundry. Verificamos as evidências públicas; os resultados são informados pelo fornecedor.
truefoundry.com- Última verificação
- 9 de out. de 2026
Abrir a captura da fonte O que o estudo de caso afirma e o que verificamos
O que comparamos com a página.
- O número: ~55%Verificado
Impresso palavra por palavra na página, perto do nome de Wadhwani AI.
- O trecho citado acimaVerificado
Copiado palavra por palavra da página, perto do nome de Wadhwani AI.
- Wadhwani AI usa TrueFoundryVerificado
Linha de nível Confirmado.
- O resultado em siNão verificado
Nós o citamos; não o medimos.
Scale the application to handle 10X Requests per second compared to the managed ML Service. Reduce the cloud cost incurred by ~55% with the same level of reliability and performance.