[Model] Add Inkling compressed-tensors dynamic FP8 support (#48876)

Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
This commit is contained in:
Krishna Teja Chitty-Venkata
2026-07-28 19:27:01 -07:00
committed by GitHub
co-authored by mgoin OpenAI Codex
parent 54ab69b14e
commit 17a74b745b
2 changed files with 29 additions and 0 deletions
+3
View File
@@ -589,6 +589,9 @@ class InklingMoE(nn.Module):
param.data[lids] = vals.reshape(len(gids), *param.shape[1:]).to(
param.device
)
elif key == "w2_weight_scale" and weight.shape[-1] == 1:
# Per-output-channel scales are replicated across TP ranks.
param.data[lids] = weight[gids].to(device=param.device, dtype=param.dtype)
elif key.startswith("w13"):
# Checkpoint w13 rows are interleaved [g0, u0, g1, u1, ...]; the
# fused param layout is [w1(gate); w3(up)]. The TP-local rows form