Article
Introducing SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
nvidia
• • 48
Alex Steiner
einsteiner1983
AI & ML interests
Data Science
Recent Activity
new activity 6 days ago
canada-quant/GLM-5.2-W4A16-MTP:Can you run NVFP4 + Marlin? new activity 6 days ago
canada-quant/GLM-5.2-W4A16-MTP:Can you run NVFP4 + Marlin? upvoted an article 4 months ago
Introducing SPEED-Bench: A Unified and Diverse Benchmark for Speculative DecodingOrganizations
upvoted an article 4 months ago
upvoted an article 8 months ago
Article
ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases
QuentinJG
• • 67