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 15, 04:45 UTC
[Doc] Rename page titles (#20130)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Jun 26, 2025 at 23:18 UTC
34878a0b481bbbb65bf17923b1eae5ebbb56f896
5 files changed
+7
-7
docs/contributing/incremental_build.md
+1
-1
@@ -1,4 +1,4 @@
1
-# Incremental Compilation Workflow for vLLM Development
1
+# Incremental Compilation Workflow
2
3
When working on vLLM's C++/CUDA kernels located in the `csrc/` directory, recompiling the entire project with `uv pip install -e .` for every change can be time-consuming. An incremental compilation workflow using CMake allows for faster iteration by only recompiling the necessary components after an initial setup. This guide details how to set up and use such a workflow, which complements your editable Python installation.
4
docs/contributing/model/README.md
+3
-3
@@ -14,9 +14,9 @@ However, this can be more complex for models that include new operators (e.g., a
14
15
Read through these pages for a step-by-step guide:
16
17
-- [Implementing a Basic Model](basic.md)
18
-- [Registering a Model to vLLM](registration.md)
19
-- [Writing Unit Tests](tests.md)
17
+- [Basic Model](basic.md)
18
+- [Registering a Model](registration.md)
19
+- [Unit Testing](tests.md)
20
- [Multi-Modal Support](multimodal.md)
21
22
!!! tip
docs/contributing/model/basic.md
+1
-1
@@ -1,5 +1,5 @@
1
---
2
-title: Implementing a Basic Model
2
+title: Basic Model
3
---
4
[](){ #new-model-basic }
5
docs/contributing/model/registration.md
+1
-1
@@ -1,5 +1,5 @@
1
---
2
-title: Registering a Model to vLLM
2
+title: Registering a Model
3
---
4
[](){ #new-model-registration }
5
docs/contributing/model/tests.md
+1
-1
@@ -1,5 +1,5 @@
1
---
2
-title: Writing Unit Tests
2
+title: Unit Testing
3
---
4
[](){ #new-model-tests }
5