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] Add a start tag to build.inc.md (#26747)
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
Michael Yao committed
Oct 14, 2025 at 12:51 UTC
2e36cdbe2b4bff4370a02105fdfbdd015d6ec4e8
2 files changed
+3
-4
docs/getting_started/installation/cpu/arm.inc.md
+1
-1
@@ -23,7 +23,7 @@ ARM CPU backend currently supports Float32, FP16 and BFloat16 datatypes.
23
# --8<-- [end:pre-built-wheels]
24
# --8<-- [start:build-wheel-from-source]
25
26
---8<-- "docs/getting_started/installation/cpu/build.inc.md"
26
+--8<-- "docs/getting_started/installation/cpu/build.inc.md:extra-information"
27
28
Testing has been conducted on AWS Graviton3 instances for compatibility.
29
docs/getting_started/installation/cpu/build.inc.md
+2
-3
@@ -1,3 +1,5 @@
1
+# --8<-- [start:extra-information]
2
+
3
First, install the recommended compiler. We recommend using `gcc/g++ >= 12.3.0` as the default compiler to avoid potential problems. For example, on Ubuntu 22.4, you can run:
4
5
```bash
@@ -39,7 +41,4 @@ If you want to develop vLLM, install it in editable mode instead.
41
VLLM_TARGET_DEVICE=cpu python setup.py develop
42
```
43
42
-!!! note
43
- If you are building vLLM from source and not using the pre-built images, remember to set `LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:$LD_PRELOAD"` on x86 machines before running vLLM.
44
-
44
# --8<-- [end:extra-information]