Elias Tatros

cgelias

·

AI & ML interests

None yet

Recent Activity

liked a model 1 day ago

sakamakismile/Qwen3.6-27B-MTP-pi-tune-NVFP4

new activity 2 days ago

nvidia/Qwen3.6-27B-NVFP4:NVFP4 vs FP8 on an RTX PRO 6000 Blackwell (vLLM 0.24): sadly, FP4 is still not faster than FP8 - Qwen3.6‑27B

new activity 2 days ago

nvidia/Qwen3.6-27B-NVFP4:vLLM + HGX B200: Your GPU does not have native support for FP4 computation but FP4 quantization is being used.

View all activity

Organizations

New activity in nvidia/Qwen3.6-27B-NVFP4 2 days ago

NVFP4 vs FP8 on an RTX PRO 6000 Blackwell (vLLM 0.24): sadly, FP4 is still not faster than FP8 - Qwen3.6‑27B

#8 opened 2 days ago by

vLLM + HGX B200: Your GPU does not have native support for FP4 computation but FP4 quantization is being used.

#12 opened 2 days ago by

New activity in sakamakismile/Qwen3.6-27B-Text-NVFP4-MTP 2 months ago

--enable-prefix-caching and Feedback from HGX B200 Deployment

#5 opened 2 months ago by