Projects / Self-distillation for speculative decoding. Complementary to KV cache optimization.
?

Self-distillation for speculative decoding. Complementary to KV cache optimization.

https://arxiv.org/abs/2603.23911 ↗
other Tracked by 1 project
Notes

Self-distillation for speculative decoding. Complementary to KV cache optimization.

Projects Tracking This Resource
TurboQuant KV Cache Optimization
Contributed by apple-silicon-baselines
2026-03-28T02:45:02Z