We have 7 of 34 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
DSpark-style parallel drafters have made speculative decoding highly effective, yet their draft phase remains serialized on the critical path of every round. Parallel speculative decoding (PSD) overlaps drafting with verification, yet existing methods must guess the accepted prefix and bonus token in advance: a wrong g...
This work proposes AdaptCore, an adaptive framework for universally high-performance MatMul on Ascend NPUs, which systematically decouples operator optimization into spatial tiling and instruction orchestration and integrates a composable optimization library with a deterministic analytical performance model.
This paper systematically analyzes failures encountered during large-scale RL training on the Huawei Ascend platform, summarizes representative failure types, and identifies three model-side factors relevant to fault reproduction.
Results show that template-anchored decomposition and stage-specific GPU execution can scale matrix completion beyond device-memory capacity, and show that template-anchored decomposition and stage-specific GPU execution can scale matrix completion beyond device-memory capacity.
SpecLA is presented, a speculative decoding runtime for stateful linear-attention models that verifies chains and trees with topology-aware kernels, stores compact factors produced during verification to recover accepted states, and uses confidence pruning plus a target-aligned EAGLE-style drafter to feed useful candid...
MISA-T, a routing-layer admission policy for mixed rollout serving that combines adaptive session admission, workload-aware KV-capacity allocation, and residency-time-aware KV accounting, is presented.
BCE is presented, a GPU-co-designed, block-centric engine that makes range-top-k efficient by exposing a reusable intermediate representation of the data, and achieves sub-millisecond query latency and up to 308 × higher throughput than state-of-the-art GPU baselines, while performing billion-scale dynamic updates in m...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
