601
edits
Changes
Jump to navigation
Jump to search
mLine 9:
Line 9: + − + − +
no edit summary
-->
-->
</noinclude>
</noinclude>
* 2026-07-22, [https://doi.org/10.1016/j.fsidi.2026.302114 Forensic Analysis of Container Snapshot Chains for Post-event Reconstruction]
* 2026-06-25, [https://is.muni.cz/th/c4unc/ Elastic Resource Management for Heterogenous Container-Based Clouds]
* 2026-06-25, [https://is.muni.cz/th/c4unc/ Elastic Resource Management for Heterogenous Container-Based Clouds]
* 2026-06-01, [https://developer.nvidia.com/blog/nvidia-dynamo-snapshot-fast-startup-for-inference-workloads-on-kubernetes/ NVIDIA Dynamo Snapshot: Fast Startup for Inference Workloads on Kubernetes]
* 2026-06-01, [https://developer.nvidia.com/blog/nvidia-dynamo-snapshot-fast-startup-for-inference-workloads-on-kubernetes/ NVIDIA Dynamo Snapshot: Fast Startup for Inference Workloads on Kubernetes]
* 2026-07-27, [https://radostin.io/files/stoyanov-dfrws-usa-2026.pdf Forensic Analysis of Container Snapshot Chains for Post-Event Reconstruction]
* 2026-07-27, [https://radostin.io/files/stoyanov-dfrws-usa-2026.pdf Forensic Analysis of Container Snapshot Chains for Post-Event Reconstruction]
* 2026-06-29, [https://j9s.io/posts/fast_vllm/ Fast vLLM: cutting cold starts by 20x]
* 2026-06-29, [https://j9s.io/posts/fast_vllm/ Fast vLLM: cutting cold starts by 20x]
* 2026-04-27, [https://radostin.io/files/stoyanov-euromlsys-2026.pdf Towards On-the-Fly Snapshot Memory Compression for Low-Latency Elastic Inference Serving Systems]
* 2026-04-27, [https://doi.org/10.1145/3805621.3807612 Towards On-the-Fly Snapshot Memory Compression for Low-Latency Elastic Inference Serving Systems]
* 2026-04-06, [https://fergusfinn.com/blog/fast-sglang-starts/ Cloudburst: 70x faster cold(ish) starts for SGLang]
* 2026-04-06, [https://fergusfinn.com/blog/fast-sglang-starts/ Cloudburst: 70x faster cold(ish) starts for SGLang]
* 2026-02-24, [https://www.usenix.org/conference/fast26/presentation/zeng GPU Checkpoint/Restore Made Fast and Lightweight]
* 2026-02-24, [https://www.usenix.org/conference/fast26/presentation/zeng GPU Checkpoint/Restore Made Fast and Lightweight]
* 2026-01-21, [https://kubernetes.io/blog/2026/01/21/introducing-checkpoint-restore-wg/ Announcing the Checkpoint/Restore Working Group]
* 2026-01-21, [https://kubernetes.io/blog/2026/01/21/introducing-checkpoint-restore-wg/ Announcing the Checkpoint/Restore Working Group]
* 2025-11-17, [https://radostin.io/files/stoyanov-canopie-hpc-2025.pdf Engine-Agnostic Model Hot-Swapping for Cost-Effective LLM Inference]
* 2025-11-17, [https://doi.org/10.1145/3731599.3767354 Engine-Agnostic Model Hot-Swapping for Cost-Effective LLM Inference]
<!------------------------------------------------
<!------------------------------------------------
This is to cut the rest of it for Main Page,
This is to cut the rest of it for Main Page,