@@ -40,7 +40,7 @@ There are multi-faceted challenges:
...
@@ -40,7 +40,7 @@ There are multi-faceted challenges:
-*Expensive KV cache re-computation*: When requests aren't efficiently routed, KV caches (intermediate states of transformer model) often get flushed and recomputed, leading to wasted computation cycles and increased latency. KV-aware request routing eliminates redundant KV cache regeneration, significantly boosting efficiency.([DeepSeek](https://arxiv.org/abs/2501.12948))
-*Expensive KV cache re-computation*: When requests aren't efficiently routed, KV caches (intermediate states of transformer model) often get flushed and recomputed, leading to wasted computation cycles and increased latency. KV-aware request routing eliminates redundant KV cache regeneration, significantly boosting efficiency.([DeepSeek](https://arxiv.org/abs/2501.12948))
-*Memory bottlenecks*: Large-scale inference workloads demand extensive KV cache storage, which can quickly overwhelm GPU memory capacity. KV cache offloading across memory hierarchies (HBM, DDR, NVMe or remote storage) enables models to scale beyond GPU memory limits and speeds up latency. ([Mooncake](https://github.com/kvcache-ai/Mooncake/blob/main/doc/en/mooncake-store-preview.md), [AIBrix](https://blog.vllm.ai/2025/02/21/aibrix-release.html), [LMCache](https://lmcache.ai/))
-*Memory bottlenecks*: Large-scale inference workloads demand extensive KV cache storage, which can quickly overwhelm GPU memory capacity. KV cache offloading across memory hierarchies (HBM, DDR, NVMe or remote storage) enables models to scale beyond GPU memory limits and speeds up latency. ([Mooncake](https://github.com/kvcache-ai/Mooncake/blob/main/doc/en/mooncake-store.md), [AIBrix](https://blog.vllm.ai/2025/02/21/aibrix-release.html), [LMCache](https://lmcache.ai/))
-*Fluctuating demand and inefficient GPU allocation*: Inference workloads are use-case specific and dynamic—demand surges inherently cause unpredictably, yet traditional serving stacks allocate GPUs statically. Dynamic GPU scheduling ensures that resources are allocated based on real-time demand, preventing over-provisioning and improving utilization ([AzureTrace](https://github.com/Azure/AzurePublicDataset))
-*Fluctuating demand and inefficient GPU allocation*: Inference workloads are use-case specific and dynamic—demand surges inherently cause unpredictably, yet traditional serving stacks allocate GPUs statically. Dynamic GPU scheduling ensures that resources are allocated based on real-time demand, preventing over-provisioning and improving utilization ([AzureTrace](https://github.com/Azure/AzurePublicDataset))
