biondizzle ff579c9767 fix: use NVFP4 SymmBuffer (2x SF size for group_size=16) ...

The NVFP4 mega_moe kernel needs a larger symmetric buffer because
group_size=16 produces 2x more scale factor entries than MXFP4's 32.
Switch from deep_gemm.get_symm_buffer_for_mega_moe to
deep_gemm.mega.nvfp4.get_symm_buffer_for_nvfp4_mega_moe.

2026-05-11 07:49:11 +00:00

..

deepseek_v4.py

fix: use NVFP4 SymmBuffer (2x SF size for group_size=16)

2026-05-11 07:49:11 +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