A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 03:00 UTC
Fix `autodoc` directives (#4272)
Co-authored-by: Harry Mellor <hmellor@oxts.com>
Harry Mellor committed
Apr 23, 2024 at 02:53 UTC
34128a697ed2dd4d88a9829f35445fbfc5b85c64
3 files changed
+7
-7
docs/source/dev/engine/async_llm_engine.rst
+2
-3
@@ -1,7 +1,6 @@
1
-
1
AsyncLLMEngine
2
=================================
3
5
-.. autoclass:: vllm.engine.async_llm_engine.AsyncLLMEngine
6
- :members: generate, abort
4
+.. autoclass:: vllm.AsyncLLMEngine
5
+ :members:
6
:show-inheritance:
docs/source/dev/engine/llm_engine.rst
+3
-3
@@ -1,6 +1,6 @@
1
LLMEngine
2
=================================
3
4
-.. autoclass:: vllm.engine.llm_engine.LLMEngine
5
- :members: add_request, abort_request, step
6
- :show-inheritance:
\ No newline at end of file
4
+.. autoclass:: vllm.LLMEngine
5
+ :members:
6
+ :show-inheritance:
docs/source/dev/sampling_params.rst
+2
-1
@@ -1,4 +1,5 @@
1
Sampling Params
2
===============
3
4
-.. automodule:: vllm.sampling_params.SamplingParams
\ No newline at end of file
4
+.. autoclass:: vllm.SamplingParams
5
+ :members: