biondizzle c85b84b0fe fix: staging kernel outputs unpacked E2M1 (1 byte/element, not packed 2/byte) ...

Matches the SMEM layout: float_e2m1_unpacksmem_t is 1 byte/element.
L1→L2 handoff uses unpacked format (same byte count as FP8).
No bandwidth savings at L1→L2 for v1 — can optimize later.

2026-05-11 21:29:33 +00:00

..

deepseek_v4.py

fix: same reshape fix in main patch file

2026-05-11 21:05:54 +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

staging_kernel.py

fix: staging kernel outputs unpacked E2M1 (1 byte/element, not packed 2/byte)

2026-05-11 21:29:33 +00:00