Article
Google Released Gemma-4 Four Days Ago. We Already Made It 1.72× Faster.
lujangusface
• • 2Gustavo A Lujan PRO
lujangusface
AI & ML interests
None yet
Recent Activity
published an article 29 days ago
SpecJAX: A Speculative Decoding Library for TPUs published an article about 1 month ago
We Pitted the Cheapest TPU Against an NVIDIA L4. Here's What 6 Experiments Revealed. published an article about 1 month ago
1.37x Faster on Alibaba's 80B Code Model: EAGLE3 for Qwen3-Coder-NextOrganizations
upvoted an article about 1 month ago
upvoted an article about 2 months ago
Article
Speculative Decoding in Practice: How EAGLE3 Makes LLMs Faster Without Changing Their Outputs
lujangusface
• • 8