Article
Speculative Decoding in Practice: How EAGLE3 Makes LLMs Faster Without Changing Their Outputs
•
2
Gustavo A Lujan PRO
lujangusface
AI & ML interests
None yet
Recent Activity
upvoted an article about 18 hours ago
Speculative Decoding in Practice: How EAGLE3 Makes LLMs Faster Without Changing Their Outputs published an article about 18 hours ago
Speculative Decoding in Practice: How EAGLE3 Makes LLMs Faster Without Changing Their Outputs updated a model about 23 hours ago
thoughtworks/MiniMax-M2.5-Eagle3-exp-gOrganizations
upvoted an article about 18 hours ago
published an article about 18 hours ago
Article
Speculative Decoding in Practice: How EAGLE3 Makes LLMs Faster Without Changing Their Outputs
•
2
updated a
model about 23 hours ago
published a
model about 23 hours ago
[bot] Conversion to Parquet
#1 opened 23 days ago
by 
parquet-converter
published 8
models 6 days ago
thoughtworks/Qwen3-32B-Eagle3
Text Generation • Updated • 255
thoughtworks/Qwen3-14B-Eagle3
Text Generation • Updated • 245
thoughtworks/Qwen3-8B-Eagle3
Text Generation • Updated • 247
thoughtworks/DeepSeek-R1-Distill-Qwen-14B-Eagle3
Text Generation • Updated • 280
thoughtworks/DeepSeek-R1-Distill-Qwen-7B-Eagle3
Text Generation • Updated • 273
thoughtworks/Qwen2.5-14B-Instruct-Eagle3
Text Generation • Updated • 232
thoughtworks/Llama-3.1-8B-Instruct-Eagle3
Text Generation • Updated • 228
thoughtworks/Llama-3.2-3B-Instruct-Eagle3
Text Generation • Updated • 266
updated 7
models 6 days ago
thoughtworks/Qwen3-14B-Eagle3
Text Generation • Updated • 245
thoughtworks/Qwen3-8B-Eagle3
Text Generation • Updated • 247
thoughtworks/DeepSeek-R1-Distill-Qwen-14B-Eagle3
Text Generation • Updated • 280
thoughtworks/DeepSeek-R1-Distill-Qwen-7B-Eagle3
Text Generation • Updated • 273
thoughtworks/Qwen2.5-14B-Instruct-Eagle3
Text Generation • Updated • 232
thoughtworks/Qwen2.5-7B-Instruct-Eagle3
Text Generation • Updated • 270
thoughtworks/Llama-3.1-8B-Instruct-Eagle3
Text Generation • Updated • 228