Optimizing GLM4-MoE for Production: 65% Faster TTFT with SGLang
• 11
Inference Provider
VERIFIED
9,272,152 monthly requests
AI & ML interests
AI inference, open-source model APIs, serverless GPUs, and on-demand GPU instances.
Articles
novita/kimi-k2.6-dspark
Text Generation • 3B • Updated • 85 • 16
novita/kimi-k2.7-code-dspark
Text Generation • 3B • Updated • 230 • 7
novita/kimi-k2.7-code-eagle3-mla
Text Generation • 2B • Updated • 390 • 3
novita/Behemoth-123B-v1.2-FP8
123B • Updated • 12
novita/Cydonia-24B-v3-FP8
24B • Updated • 9
novita/NemoMix-Unleashed-12B-FP8
12B • Updated • 12 • 1
novita/MN-12B-Mag-Mell-R1-FP8
12B • Updated • 8
novita/Deepseek-R1-0528-W4AFP8
349B • Updated • 27 • 1
novita/Deepseek-V3.1-W4AFP8
349B • Updated • 22
novita/Deepseek-R1-W4AFP8
349B • Updated • 6
novita/Deepseek-V3-0324-W4AFP8
349B • Updated • 12 • 1
novita/Sao10K-L3-8B-Stheno-v3.2-AWQ-FP8
8B • Updated • 1
novita/inflatebot-MN-12B-Mag-Mell-R1-AWQ-FP8
12B • Updated
novita/DeepSeek-R1-Distill-Llama-70B-w8a8kv8-s888
71B • Updated • 6 • 2