-
Notifications
You must be signed in to change notification settings - Fork 8
Pull requests: NVIDIA-NeMo/Export-Deploy
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Fix building doc and remove all nemo 2.0 docs
deploy
docs-only
With great power comes great responsibility.
documentation
Improvements or additions to documentation
export
LLM
multimodal
TensorRT-LLM
#615
opened Feb 21, 2026 by
oyilmaz-nvidia
Loading…
Set assume_32_bit_indexing to False for vllm
export
tests
vLLM
#614
opened Feb 21, 2026 by
chtruong814
Loading…
Set materialize_only_last_token_logits=False when log_probs = True
deploy
LLM
#613
opened Feb 20, 2026 by
athitten
Loading…
Fix multimodal deployment sampling params
deploy
multimodal
scripts
tests
#602
opened Feb 17, 2026 by
meatybobby
Loading…
Add max-model-len param for vLLM
deploy
export
LLM
r0.3.0
r0.3.0
scripts
tests
vLLM
#502
opened Nov 4, 2025 by
oyilmaz-nvidia
Loading…
Update MM docs
deploy
documentation
Improvements or additions to documentation
export
multimodal
TensorRT-LLM
#498
opened Oct 31, 2025 by
meatybobby
Loading…
Fix tokenizer path if it is not correct
deploy
LLM
r0.3.0
r0.3.0
scripts
tests
#485
opened Oct 22, 2025 by
oyilmaz-nvidia
Loading…
ProTip!
Follow long discussions with comments:>50.