[Core] Consolidate prompt arguments to LLM engines (#4328)
Co-authored-by: Roger Wang <ywang@roblox.com>
This commit is contained in:
co-authored by
Roger Wang
parent
290f4ada2b
commit
5ae5ed1e60
@@ -68,13 +68,6 @@ Documentation
|
||||
getting_started/quickstart
|
||||
getting_started/examples/examples_index
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:caption: Offline Inference
|
||||
|
||||
offline_inference/llm
|
||||
offline_inference/sampling_params
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:caption: Serving
|
||||
@@ -108,7 +101,9 @@ Documentation
|
||||
.. toctree::
|
||||
:maxdepth: 2
|
||||
:caption: Developer Documentation
|
||||
|
||||
|
||||
dev/sampling_params
|
||||
dev/offline_inference/offline_index
|
||||
dev/engine/engine_index
|
||||
dev/kernel/paged_attention
|
||||
dev/dockerfile/dockerfile
|
||||
|
||||
Reference in New Issue
Block a user