arXiv:2607. 02630v1 Announce Type: cross Abstract: Hardware accelerators now sit on the critical path of online serving.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2607. 02043v1 Announce Type: cross Abstract: Disaggregated LLM serving runs prefill and decode on separate GPU pools to keep the two phases from interfering.
arXiv:2512. 10236v2 Announce Type: replace-cross Abstract: Modern ML workloads demand distributing training and inference across multiple GPUs.
We report operational experience full-fine-tuning a 32. 76B-parameter dense model (Qwen3-32B) on 16 x NVIDIA B300 (two nodes, FSDP / ZeRO-3) -- among the first published field accounts on this accelerator.
arXiv:2608. 05944v1 Announce Type: cross Abstract: We report operational experience full-fine-tuning a 32.
arXiv:2608. 12123v1 Announce Type: cross Abstract: LLM-agent services repeatedly execute small deterministic transitions between model and tool calls: route an outcome, update state, and emit the next effect.
arXiv:2607. 04668v1 Announce Type: cross Abstract: On-device LLM decoding is a hard-barriered CPU-SIMD computation that wants every core for milliseconds per token, while the rest of the OS wants those same cores continuously.