Andrea Moccia

brokenlander

·

AI & ML interests

None yet

Recent Activity

new activity 5 days ago

nvidia/GLM-5.3-Flash-NVFP4:MTP layer is unquantized but missing from exclude_modules, so vLLM cannot load it for speculative decoding

upvoted a collection over 1 year ago

Unsloth 4-bit Dynamic Quants

View all activity

Organizations

None yet

New activity in nvidia/GLM-5.3-Flash-NVFP4 5 days ago

MTP layer is unquantized but missing from exclude_modules, so vLLM cannot load it for speculative decoding

#13 opened 5 days ago by

upvoted a collection over 1 year ago

Unsloth 4-bit Dynamic Quants

Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit • 28 items • Updated Aug 26 • 97