Parallel AR-Approximation for Faster Speculative Decoding (https://arxiv.org/abs/2606.03819)
Peer Rheinboldt
peerrh
AI & ML interests
None yet
Recent Activity
updated a model 9 days ago
peerrh/treeflash-qwen3-coder-30b-a3b updated a model 9 days ago
peerrh/treeflash-qwen3-4b updated a model 9 days ago
peerrh/treeflash-qwen3-8bOrganizations
None yet
models 9
peerrh/treeflash-qwen3-coder-30b-a3b
Text Generation • 0.5B • Updated • 44
peerrh/treeflash-qwen3-4b
Text Generation • 0.7B • Updated • 111
peerrh/treeflash-qwen3-8b
Text Generation • 1B • Updated • 77
peerrh/llama-3.1-8b-steered
Updated • 1
peerrh/llama-3.1-8b-distilled
Updated • 1
peerrh/qwen3-8b-distilled
Updated • 1
peerrh/qwen3-14b-steered
Updated • 1
peerrh/qwen3-14b-distilled
Updated • 1
peerrh/qwen3-8b-steered
Updated • 3
datasets 0
None public yet