biondizzle a36bf47f11 fix: use tl.split instead of indexing for E2M1 pair packing ...

Triton doesn't support constexpr tensor indexing (e2m1_pairs[:, 0]).
Use tl.split() which splits the last axis into two tensors.

2026-05-11 22:39:38 +00:00

..

deepseek_v4.py

fix: use tl.split instead of indexing for E2M1 pair packing

2026-05-11 22:39:38 +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