mengxiangjun

omeng-nvidia

1

·

AI & ML interests

None yet

Recent Activity

new activity 21 days ago

MengYuNV/flashinfer-trace:feat(moe): add BF16 MoE definitions, workloads, and CUTLASS SM90 solutions for Qwen3-235B

updated a model about 1 year ago

omeng-nvidia/Qwen3-32-FP8-pertensor

published a model about 1 year ago

omeng-nvidia/Qwen3-32-FP8-pertensor

View all activity

Organizations

omeng-nvidia 's models 4

omeng-nvidia/Qwen3-32-FP8-pertensor

33B • Updated Jul 23, 2025 • 3

omeng-nvidia/Qwen3-32B_nvfp4_hf

19B • Updated Jul 22, 2025 • 12

omeng-nvidia/saved_models_Qwen3-30B-A3B_nvfp4_hf

17B • Updated May 28, 2025 • 9 • 2

omeng-nvidia/saved_models_Qwen3-30B-A3B_fp8_hf

31B • Updated May 28, 2025 • 5