[Doc] Feature compatibility matrix

Signed-off-by: Wallas Santos <wallashss@ibm.com>
vllm-project · Oct 8, 2024 · 10f4fab · 10f4fab
1 parent e0dbdb0
commit 10f4fab
Show file tree

Hide file tree

Showing 13 changed files with 467 additions and 0 deletions.
diff --git a/docs/source/index.rst b/docs/source/index.rst
@@ -86,6 +86,7 @@ Documentation
    serving/usage_stats
    serving/integrations
    serving/tensorizer
+   serving/compatibility_matrix
    serving/faq
 
 .. toctree::

diff --git a/docs/source/models/performance.rst b/docs/source/models/performance.rst
@@ -22,6 +22,8 @@ If you frequently encounter preemptions from the vLLM engine, consider the follo
 
 You can also monitor the number of preemption requests through Prometheus metrics exposed by the vLLM. Additionally, you can log the cumulative number of preemption requests by setting disable_log_stats=False.
 
+.. _chunked-prefill:
+
 Chunked Prefill
 ---------------
 vLLM supports an experimental feature chunked prefill. Chunked prefill allows to chunk large prefills into smaller chunks and batch them together with decode requests.