Sustained contributions lead to lasting and impactful transformations.
#SavetheChildrenHK #ChildGuardian #MonthlyDonation
HONG KONG, Aug. 22, 2024 /PRNewswire/ -- Data released by the Hong Kong Government Education Bureau indicates that in 2023, there were over 30 reported instances of suspected suicides involving primary and secondary school students, marking a five-year high. The recent surge in suicide cases underscores the significance of extending support beyond mere material assistance; emotional sustenance and empathy for children are equally imperative.
Established over a century ago, Save the Children stands as the pioneering independent children's organisation globally, dedicated to effecting immediate and enduring positive changes in the lives of children worldwide, thereby shaping a brighter collective future. Save the Children has played a vital role in enhancing the welfare of children in Hong Kong and over 120 countries and regions, guaranteeing their health, joy, education, and security.
This year marks the 15th anniversary of Save the Children Hong Kong, has worked closely with underprivileged children to safeguard their personal safety and enhance their mental well-being, emphasizing the advocacy for the children's welfare. Save the Children Hong Kong not only aids local children but also provides assistance worldwide, helping children affected by conflicts such as the Russian-Ukrainian war, the Syrian earthquake, and violence in regions like Gaza, Israel, and Sudan. Save the Children Hong Kong offers both physical and emotional support to children affected by wars and natural disasters, showcasing its commitment to safeguarding children's welfare globally.
Nagi is a happy and cheeky little boy, but his world turned upside down when he had to flee violence in Sudan. His family found temporary accommodation but didn't have any of their belongings. Save the Children was able to help by supplying the family with things they needed, as well as creating a child friendly space where Nagi could learn and play safely.
Maha, 10, was out collecting firewood near her home in Yemen when she stepped on a landmine - and her life changed forever. Her injuries were so severe, she was rushed to hospital where she needed urgent surgery. Save the Children covered all her medical costs and provided ongoing psycho-social support. Maha is now back at school, where she loves drawing.
17 year Olena was worried about her education when her school was destroyed during the war in Ukraine. Save the Children created a new safe place for the students to finish their studies. Before graduation, they visited their old school to take special yearbook photos that would remind them of the school where they had many happy memories.
Explore additional stories about the sponsored children: https://savethechildren.org.hk/wp-content/uploads/2024/02/Impact-Report-2023.pdf
"Let children grow up healthily and happily" is no longer just a slogan.
"Children are the future pillars of society," a well-known saying that emphasizes the crucial role each child plays in shaping a brighter tomorrow for all. Ensuring a child's future transcends mere provision of basic needs like food and clothing. While temporary assistance offers immediate physical care to distressed children, their emotional well-being is equally significant. Daily stability and support lay the foundation for psychological security, empowering them to navigate life confidently and explore endless opportunities.
This is the purpose of the Save the Children's Child Guardian program. Thanks to the monthly donations made by the Child Guardians, Save the Children is able to generate a steady stream of income for the development of longer-term and more effective programs for the children. When a natural disaster strikes, Save the Children is able to go to the disaster area and help the children in need immediately. After the disaster, Save the Children can continue to provide support to the children, so that Save the Children's work can be sustained.
You can shape a better future for children, leading to our bright future.
Take action now and be a Child Guardian by making a monthly donation!
Be a Child Guardian: https://savethechildren.org.hk/together-we-empower-a-happy-childhood/?utm_source=Innity&utm_medium=innityPR+ad&utm_campaign=CG
Tel： (852) 3160-8786
E-mail: hk.sponsorsupport@savethechildren.org
Website: https://savethechildren.org.hk/
Facebook: https://www.facebook.com/savethechildrenhk
Instagram: https://www.instagram.com/savethechildrenhk/
For more high-resolution images, please refer to the following links to download: Link
About Save The Children Hong Kong
Save the Children believes every child deserves a future. In Hong Kong and around the world, we do whatever it takes – every day and in times of crisis – so children can fulfil their rights to a healthy start in life, the opportunity to learn and protection from harm. With over 100 years of expertise, we are the world's first and leading independent children's organisation – transforming lives and the future we share.
Established in 2009, Save the Children Hong Kong is part of the global movement which operates in around 120 countries. We work with children, schools, families, communities and our supporters to deliver lasting change for children in Hong Kong and around the world.
Visit our website, or follow us on Facebook, Instagram, LinkedIn and YouTube.
** The press release content is from PR Newswire. Bastille Post is not involved in its creation. **
Persistent Donations Transform Children's Lives
|
Joint benchmarks on OCI H100 infrastructure showed 10x more concurrent users, 10x higher token throughput, and 7x more tokens served without adding GPUs
CAMPBELL, Calif., June 10, 2026 /PRNewswire/ -- WEKA, the AI data and memory infrastructure company, today announced production-scale benchmarks that show how organizations can improve the economics of long-context AI inference by serving more users and tokens on the same GPU footprint. The benchmarks show that WEKA's NeuralMesh™ platform with Augmented Memory Grid™ on Oracle Cloud Infrastructure (OCI) serves 10x more concurrent users, delivers 10x higher token throughput, and produces 7x more tokens per GPU than DRAM-only configurations without adding infrastructure. The results were validated on a nine-node OCI bare-metal H100 cluster with 100,000-token context windows.
"Enterprise AI workloads are pushing context windows and GPU utilization to new limits," said Pablo Selem, senior director, software development, Oracle Cloud Infrastructure. "These benchmarks show how WEKA's NeuralMesh platform with Augmented Memory Grid on OCI helps remove memory bottlenecks so customers can support larger, more demanding inference workloads without simply adding more GPUs."
Three Outcomes That Change the Math on Inference
Validated at production scale on a bare-metal H100 cluster (nine nodes, 72 GPUs, 100,000-token context windows, thousands of concurrent users), NeuralMesh with Augmented Memory Grid on OCI delivered:
- 10x more concurrent users served, without adding infrastructure. NeuralMesh with Augmented Memory Grid scaled past 5,000 concurrent users vs. about 600 for DRAM-only configurations. This eliminates the failure cliff that hits when cache saturates by expanding the active cache working set from 8.64 TiB of DRAM to 287 TiB of usable NVMe. In addition, more users per GPU means the same investment stretches further.
- 10x higher token throughput. More output from every GPU in the cluster. On OCI, NeuralMesh with Augmented Memory Grid reached approx. two million tokens per second, compared to under 200,000 for the DRAM-only baseline. For product teams running real-time AI features, including search, summarization, code assist, and multi-turn agents, the throughput determines the ceiling for how many users can be served, how fast features respond, and how much revenue the infrastructure can support.
- 7x more tokens served. Lower cost per token at scale. NeuralMesh with Augmented Memory Grid served five billion tokens, compared to 700 million for the DRAM-only baseline, in a single one-hour, 2,400-user test. For organizations running agentic workflows, DRAM saturation quietly drains GPU capacity through constant recomputation, creating a direct hit on cost per token and ROI.
"Inference is bottlenecked by how much effective memory is available to GPUs," said Liran Zvibel, CEO of WEKA. "These results prove that AI token economics aren't solved by hardware alone; they're solved by eliminating the memory wall that has been the real ceiling on what existing hardware can do. NeuralMesh with Augmented Memory Grid running on OCI brings orders of magnitude more tokens to customers in an extremely cost-efficient way."
Transforming AI Economics with Context Memory Infrastructure
As inference demand grows, AI infrastructure inefficiencies compound. Every key-value (KV) cache eviction is a tax: on GPU cycles, latency, user experience, and the cost of every token served. For long-context and agentic workloads, where inputs routinely run to 100,000 tokens or more, that tax is not a rounding error. It is a direct hit on the unit economics of every organization running production AI.
Augmented Memory Grid, a capability of NeuralMesh, solves the problem at the architectural level by decoupling KV cache from local GPU memory and storing it in a high-performance token warehouse accessible across the cluster. Any host can serve any session with cache hits intact, eliminating rigid session stickiness while delivering superior performance to DRAM, improving load balancing, and enabling clean horizontal scaling as concurrency grows. The result is persistent context memory for AI agents and the cost lever that makes long-context inference economical to run at scale.
Production-Grade Proof
OCI published the full benchmark methodology, system configuration, and results on its AI & Data Science blog on May 13, 2026. The benchmarks, executed on a nine-node OCI bare-metal H100 cluster, move beyond the prior phase of validation, which demonstrated 1000x more KV cache capacity and up to 20x faster time to first token at 128,000 tokens. This latest phase tests the full economics of inference in production: concurrency density, sustained throughput, cache persistence, and service level objective (SLO) stability when demand spikes under high load.
Available on Oracle Marketplace
NeuralMesh with Augmented Memory Grid is generally available to WEKA customers and on the Oracle Marketplace, with OCI as WEKA's exclusive cloud launch partner. Organizations running long-context inference on OCI can deploy a validated, production-ready architecture today. For more on the OCI and WEKA Augmented Memory Grid benchmark, read the OCI blog: https://blogs.oracle.com/ai-and-datascience/scaling-long-context-inference-on-oci-with-wekas-augmented-memory-grid.
About WEKA
WEKA is the AI data and memory infrastructure company transforming the economics of agentic AI. Its NeuralMesh™ platform unifies high-performance data storage with extended GPU memory, giving enterprises, AI cloud providers, and AI builders a single foundation for training, inference, and agentic workloads. With Augmented Memory Grid, NeuralMesh extends GPU memory capacity by 1000x, accelerates time to first token by up to 20x, and delivers 10x more concurrent users from the same GPU footprint, proven in production benchmarks. Trusted by 30% of the Fortune 50, WEKA enables organizations to scale AI faster, optimize GPU utilization, and reduce the cost of every token served. Learn more at www.weka.io or connect with us on LinkedIn and X.
WEKA and the W logo are registered trademarks of WekaIO, Inc. Other trade names herein may be trademarks of their respective owners.
Joint benchmarks on OCI H100 infrastructure showed 10x more concurrent users, 10x higher token throughput, and 7x more tokens served without adding GPUs
CAMPBELL, Calif., June 10, 2026 /PRNewswire/ -- WEKA, the AI data and memory infrastructure company, today announced production-scale benchmarks that show how organizations can improve the economics of long-context AI inference by serving more users and tokens on the same GPU footprint. The benchmarks show that WEKA's NeuralMesh™ platform with Augmented Memory Grid™ on Oracle Cloud Infrastructure (OCI) serves 10x more concurrent users, delivers 10x higher token throughput, and produces 7x more tokens per GPU than DRAM-only configurations without adding infrastructure. The results were validated on a nine-node OCI bare-metal H100 cluster with 100,000-token context windows.
"Enterprise AI workloads are pushing context windows and GPU utilization to new limits," said Pablo Selem, senior director, software development, Oracle Cloud Infrastructure. "These benchmarks show how WEKA's NeuralMesh platform with Augmented Memory Grid on OCI helps remove memory bottlenecks so customers can support larger, more demanding inference workloads without simply adding more GPUs."
Three Outcomes That Change the Math on Inference
Validated at production scale on a bare-metal H100 cluster (nine nodes, 72 GPUs, 100,000-token context windows, thousands of concurrent users), NeuralMesh with Augmented Memory Grid on OCI delivered:
- 10x more concurrent users served, without adding infrastructure. NeuralMesh with Augmented Memory Grid scaled past 5,000 concurrent users vs. about 600 for DRAM-only configurations. This eliminates the failure cliff that hits when cache saturates by expanding the active cache working set from 8.64 TiB of DRAM to 287 TiB of usable NVMe. In addition, more users per GPU means the same investment stretches further.
- 10x higher token throughput. More output from every GPU in the cluster. On OCI, NeuralMesh with Augmented Memory Grid reached approx. two million tokens per second, compared to under 200,000 for the DRAM-only baseline. For product teams running real-time AI features, including search, summarization, code assist, and multi-turn agents, the throughput determines the ceiling for how many users can be served, how fast features respond, and how much revenue the infrastructure can support.
- 7x more tokens served. Lower cost per token at scale. NeuralMesh with Augmented Memory Grid served five billion tokens, compared to 700 million for the DRAM-only baseline, in a single one-hour, 2,400-user test. For organizations running agentic workflows, DRAM saturation quietly drains GPU capacity through constant recomputation, creating a direct hit on cost per token and ROI.
"Inference is bottlenecked by how much effective memory is available to GPUs," said Liran Zvibel, CEO of WEKA. "These results prove that AI token economics aren't solved by hardware alone; they're solved by eliminating the memory wall that has been the real ceiling on what existing hardware can do. NeuralMesh with Augmented Memory Grid running on OCI brings orders of magnitude more tokens to customers in an extremely cost-efficient way."
Transforming AI Economics with Context Memory Infrastructure
As inference demand grows, AI infrastructure inefficiencies compound. Every key-value (KV) cache eviction is a tax: on GPU cycles, latency, user experience, and the cost of every token served. For long-context and agentic workloads, where inputs routinely run to 100,000 tokens or more, that tax is not a rounding error. It is a direct hit on the unit economics of every organization running production AI.
Augmented Memory Grid, a capability of NeuralMesh, solves the problem at the architectural level by decoupling KV cache from local GPU memory and storing it in a high-performance token warehouse accessible across the cluster. Any host can serve any session with cache hits intact, eliminating rigid session stickiness while delivering superior performance to DRAM, improving load balancing, and enabling clean horizontal scaling as concurrency grows. The result is persistent context memory for AI agents and the cost lever that makes long-context inference economical to run at scale.
Production-Grade Proof
OCI published the full benchmark methodology, system configuration, and results on its AI & Data Science blog on May 13, 2026. The benchmarks, executed on a nine-node OCI bare-metal H100 cluster, move beyond the prior phase of validation, which demonstrated 1000x more KV cache capacity and up to 20x faster time to first token at 128,000 tokens. This latest phase tests the full economics of inference in production: concurrency density, sustained throughput, cache persistence, and service level objective (SLO) stability when demand spikes under high load.
Available on Oracle Marketplace
NeuralMesh with Augmented Memory Grid is generally available to WEKA customers and on the Oracle Marketplace, with OCI as WEKA's exclusive cloud launch partner. Organizations running long-context inference on OCI can deploy a validated, production-ready architecture today. For more on the OCI and WEKA Augmented Memory Grid benchmark, read the OCI blog: https://blogs.oracle.com/ai-and-datascience/scaling-long-context-inference-on-oci-with-wekas-augmented-memory-grid.
About WEKA
WEKA is the AI data and memory infrastructure company transforming the economics of agentic AI. Its NeuralMesh™ platform unifies high-performance data storage with extended GPU memory, giving enterprises, AI cloud providers, and AI builders a single foundation for training, inference, and agentic workloads. With Augmented Memory Grid, NeuralMesh extends GPU memory capacity by 1000x, accelerates time to first token by up to 20x, and delivers 10x more concurrent users from the same GPU footprint, proven in production benchmarks. Trusted by 30% of the Fortune 50, WEKA enables organizations to scale AI faster, optimize GPU utilization, and reduce the cost of every token served. Learn more at www.weka.io or connect with us on LinkedIn and X.
WEKA and the W logo are registered trademarks of WekaIO, Inc. Other trade names herein may be trademarks of their respective owners.
** This press release is distributed by PR Newswire through automated distribution system, for which the client assumes full responsibility. **
WEKA and Oracle Cloud Infrastructure Validate 10x Throughput Gains for Long-Context AI Inference
