biondizzle 67f9086a26 Fix critical dequantization bug: remove input_scale from weight dequant ...

input_scale is for ACTIVATIONS, not weights. The correct NVFP4 weight
dequantization formula is: weight_bf16 = e2m1_value * block_scale * global_scale

Including input_scale made weights ~5000x too small, causing completely
garbled output (multilingual gibberish with repeating patterns).

2026-05-11 02:23:26 +00:00

..

deepseek_v4.py

Fix critical dequantization bug: remove input_scale from weight dequant

2026-05-11 02:23:26 +00:00

deepseek_v4.py.bak

S11: Fixed substr mapping, stacking, suffix, and o_a_proj - loads weights but attention forward uses FP8 einsum incompatible with NVFP4

2026-05-10 17:45:53 +00:00

deepseek_v4.py.s11

S11: Fixed substr mapping, stacking, suffix, and o_a_proj - loads weights but attention forward uses FP8 einsum incompatible with NVFP4

2026-05-10 17:45:53 +00:00

patch_finegrained_fp8_blackwell.py

Add BF16 upcast script and Blackwell DeepGEMM patch

2026-05-07 14:25:30 +00:00

patch_vllm_weights.py

vLLM serving: patched deepseek_v4.py, disabled mega_moe, updated docs

2026-05-10 16:14:17 +00:00

quant_module_patched.py

Add ModelOpt NVFP4 pipeline: patch, run script, README

2026-05-07 07:22:54 +00:00