Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
Show HN: Optimized vLLM for Blackwell (SM_120) – 59T/S on DeepSeek-R1
github.com/informatico-madrid
2 points
malka666
5 months ago
vLLM for Blackwell (SM_120) & Kernel 6.14. Optimized for RTX 5090. 59 t/s on DeepSeek-R1 via FlashInfer
No comment yet
Show HN: Optimized vLLM for Blackwell (SM_120) – 59T/S on DeepSeek-R1 | Heykuki News