loopyt 3486b93ac9 docs: correct what importing flag_gems actually does ... Two files claimed that importing `flag_gems` registers ATen implementations process-wide, and used that to justify vendoring. The conclusion was right for the wrong reason, and the reason was wrong enough to distort planning: it made any broader FlagGems integration look reckless. Measured instead of assumed. Hashing `torch._C._dispatch_dump_table` for `aten::rms_norm`, `aten::silu`, `aten::softmax`, `aten::topk`, `aten::lerp` before and after `import flag_gems`: every table unchanged. The package `__init__` creates the `aten_lib` handle and imports the op modules; registration happens only when `enable()` or `only_enable(include=[...])` is called. And `only_enable(include=["rms_norm"])` changes exactly `aten::rms_norm` and nothing else. So the blast radius lives in `enable()`, not in the import -- which is what makes a wider integration tractable rather than risky. Vendoring still stands, for two reasons that survive the correction: the package root star-imports every op module and loads Triton TLE, which dlopen's `libflagcx` (a native dependency this deployment does not otherwise need); and the released kernel file has no internal imports, so the package bought nothing for that operator. Both files now say this, and say that it is a correction, so the next reader does not rediscover it.		2026-10-25 14:37:59 +08:00
..
vendor	docs: correct what importing flag_gems actually does	2026-10-25 14:37:59 +08:00
__init__.py	feat: add SM90 (Hopper) support for DeepSeek-V4.1 inference	2026-10-21 15:18:56 +08:00
attn_sm90.py	feat(h20): run sparse MLA on FlagGems' Triton kernel, so TileLang is no longer required	2026-10-25 14:02:58 +08:00
deep_select_sm90.py	style(sm90): satisfy ruff and add the missing type annotations	2026-10-21 17:09:08 +08:00
engram_local.py	feat(h20): route tile_kernels calls through a compat layer, so the model runs without TileLang	2026-10-22 18:10:14 +08:00
quant.py	style(sm90): satisfy ruff and add the missing type annotations	2026-10-21 17:09:08 +08:00
sparse_mla_sm90.py	style(sm90): satisfy ruff and add the missing type annotations	2026-10-21 17:09:08 +08:00
sparse_mla_triton.py	feat(h20): run sparse MLA on FlagGems' Triton kernel, so TileLang is no longer required	2026-10-25 14:02:58 +08:00
sparse_mla.py	feat(h20): run sparse MLA on FlagGems' Triton kernel, so TileLang is no longer required	2026-10-25 14:02:58 +08:00
vit_attn.py	feat: add SM90 (Hopper) support for DeepSeek-V4.1 inference	2026-10-21 15:18:56 +08:00