Seanie Lee, Dominik Wagner, Tobias Bocklet, Philipp Seeberger, Korbinian Riedhammer, Ilja Baumann
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In this work, we optimize speculative sampling for parallel hardware accelerators to improve sampling speed. We notice that substantial portions of the intermediate matrices necessary for speculative sampling can be computed concurrently. This allows us to distribute the workload across multiple GPU threads, enabling simultaneous operations on matrix segments within thread blocks. This results in profiling time improvements ranging from 6% to 13% relative to the baseline implementation, without compromising accuracy. To further accelerate speculative sampling, probability distributions parameterized by softmax are approximated by sigmoid. This approximation approach results in significantly greater relative improvements in profiling time, ranging from 37% to 94%, with a minor decline in accuracy. We conduct extensive experiments on both automatic speech recognition and summarization tasks to validate the effectiveness of our optimization methods.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.11016")
get_code_for_paper("2406.11016")
have("2406.11016")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2406.11016.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2406.11016)
Connect an agent — have() is free.