biondizzle c4891e9ee2 fix: manual FP32→UE4M3 quant in Triton staging kernel ...

Triton can't cast float8e4nv → uint8 directly. Compute E4M3 bits manually:
extract FP32 exponent/mantissa, convert to E4M3 format (4-bit exp + 3-bit mant),
handle rounding and overflow, reconstruct dequantized value for FP8 activation quantization.

2026-05-11 16:38:52 +00:00

..

deepseek_v4.py

fix: manual FP32→UE4M3 quant in Triton staging kernel

2026-05-11 16:38:52 +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