[Diffusion] Add FLUX.2-klein BF16 HWR contract

Signed-off-by: hsliuustc0106 <hsliuustc0106@users.noreply.github.com>
This commit is contained in:
hsliuustc0106 committed 2026-08-26 17:34:54 +08:00
1 parent 816335cb46
commit 44f7a6b7f7
7 files changed
+429 -35

No files matched your search

@@ -220,9 +220,12 @@ model revision and parallel layout with `required`. TP coordinates have distinct
identities, while equivalent DP replicas share them.
The current producer/consumer boundary is the model-declared final-layout BF16
contract (MiniMax H3 today). It supports ordinary-loader final layouts for TP1
and TP2 rank identities plus SP layout identities; online quantization, HSDP,
LoRA/adapted weights, and non-default load formats remain ineligible. HWR mode
contract (MiniMax H3 and `black-forest-labs/FLUX.2-klein-4B`). The FLUX.2-klein
contract covers both transformer block stacks, constructor-stable packed QKV
mapping state, BF16 parameters, and any persistent loader-owned `beta`/`eps`
buffers. It supports ordinary-loader final layouts for TP1 and TP2 rank
identities plus SP layout identities; online quantization, HSDP, LoRA/adapted
weights, and non-default load formats remain ineligible. HWR mode
`disabled`, DLO-disabled, and DLO AllGather configurations stop before source
identity or store construction and retain the existing checkpoint-mmap or
ordinary-loader path.