[Chore] Use upstream Transformers DeepseekV4Config (#61392)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
This commit is contained in:
Harry Mellor
2026-10-15 01:08:08 -07:00
committed by GitHub
co-authored by Claude Opus 5.5 mergify[bot] <37929162+mergify[bot]@users.noreply.github.com> Kevin H. Luu
parent 1c4c319792
commit b965ee564d
31 changed files with 155 additions and 120 deletions
+1 -1
View File
@@ -2344,7 +2344,7 @@ class GPUModelRunner(
# TODO(Isotr0py): Refactor mm_prefix_lm implementation
# for better readability and maintainability.
_span_pad_modulus = getattr(
hf_text_config, "mm_prefix_span_leading_pad_modulus", 0
self.model, "mm_prefix_span_leading_pad_modulus", 0
)
for req_id in self.input_batch.req_ids:
image_doc_ranges = []