[Rust Frontend] Pass vision preprocessing context for Nemotron-H (#57634)

Pass the remaining engine context-length budget to model-owned vision processors through VisionPreprocessingContext. Preserve Nemotron batched engine fields and recognize llm_config as a text_config alias.

Use the merged upstream llm-multimodal revision f0985ef65967615db2c79279aa07818499301bfd.

Co-authored-by: Codex <noreply@openai.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
This commit is contained in:
Biswa Panda
2026-09-24 14:08:26 +08:00
committed by GitHub
co-authored by Codex
parent ee2f3cdf12
commit cf78797cb7
8 changed files with 240 additions and 21 deletions
+1 -1
View File
@@ -2290,7 +2290,7 @@ checksum = "11d3d7f243d5c5a8b9bb5d6dd2b1602c0cb0b9db1621bafc7ed66e35ff9fe092"
[[package]]
name = "llm-multimodal"
version = "1.7.1"
source = "git+https://github.com/smg-project/llm-multimodal?rev=53ca0d6ea829af7477b6b63851cc70bed409bbc8#53ca0d6ea829af7477b6b63851cc70bed409bbc8"
source = "git+https://github.com/smg-project/llm-multimodal?rev=f0985ef65967615db2c79279aa07818499301bfd#f0985ef65967615db2c79279aa07818499301bfd"
dependencies = [
"anyhow",
"base64 0.22.1",