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 14, 05:30 UTC
[Docs] Move feature compatibility tables to README (#24431)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Harry Mellor committed
Sep 8, 2025 at 14:45 UTC
717fc00e98c18d183f9141393b4185ddfb6606b3
2 files changed
+6
-7
docs/.nav.yml
+1
-4
@@ -32,10 +32,7 @@ nav:
32
- models/pooling_models.md
33
- models/extensions
34
- Hardware Supported Models: models/hardware_supported_models
35
- - Features:
36
- - features/compatibility_matrix.md
37
- - features/*
38
- - features/quantization
35
+ - Features: features
36
- Developer Guide:
37
- contributing/README.md
38
- General:
docs/features/README.md
renamed
+5
-3
@@ -1,4 +1,6 @@
1
-# Compatibility Matrix
1
+# Features
2
+
3
+## Compatibility Matrix
4
5
The tables below show mutually exclusive features and the support on some hardware.
6
@@ -12,7 +14,7 @@ The symbols used have the following meanings:
14
!!! note
15
Check the ❌ or 🟠 with links to see tracking issue for unsupported feature/hardware combination.
16
15
-## Feature x Feature
17
+### Feature x Feature
18
19
<style>
20
td:not(:first-child) {
@@ -56,7 +58,7 @@ th:not(:first-child) {
58
59
[](){ #feature-x-hardware }
60
59
-## Feature x Hardware
61
+### Feature x Hardware
62
63
| Feature | Volta | Turing | Ampere | Ada | Hopper | CPU | AMD | TPU |
64
|-----------------------------------------------------------|---------------------|-----------|-----------|--------|------------|--------------------|--------|-----|