Skip to content

[doc] Update x86 CPU-inference installation doc to reflect optionality of AVX512f #22707

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Aug 12, 2025
Merged

[doc] Update x86 CPU-inference installation doc to reflect optionality of AVX512f #22707

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
2be6845
Update x86 CPU installation doc to reflect optionality of AVX512f ins…
sooraj-satheesh Aug 12, 2025
ba3885e
[doc] Correct default state of avx512 feature in cpu inference build
sooraj-satheesh Aug 12, 2025
a9c0e2e
Apply suggestions from code review (improve grammer)
sooraj-satheesh Aug 12, 2025
13e2236
Update x86.inc.md to add recommendation against avx2 cpu inference
sooraj-satheesh Aug 12, 2025
0ce45ef
Apply suggestions from code review
sooraj-satheesh Aug 12, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions docs/getting_started/installation/cpu/x86.inc.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ vLLM supports basic model inferencing and serving on x86 CPU platform, with data
# --8<-- [start:requirements]

- OS: Linux
- CPU flags: `avx512f`, `avx512_bf16` (Optional), `avx512_vnni` (Optional)
- CPU flags: `avx512f` (Recommended), `avx512_bf16` (Optional), `avx512_vnni` (Optional)

!!! tip
Use `lscpu` to check the CPU flags.
Expand All @@ -28,7 +28,7 @@ vLLM supports basic model inferencing and serving on x86 CPU platform, with data
[https://gallery.ecr.aws/q9t5s3a7/vllm-cpu-release-repo](https://gallery.ecr.aws/q9t5s3a7/vllm-cpu-release-repo)

!!! warning
If deploying the pre-built images on machines only contain `avx512f`, `Illegal instruction` error may be raised. It is recommended to build images for these machines with `--build-arg VLLM_CPU_AVX512BF16=false` and `--build-arg VLLM_CPU_AVX512VNNI=false`.
If deploying the pre-built images on machines without `avx512f`, `avx512_bf16`, or `avx512_vnni` support, an `Illegal instruction` error may be raised. It is recommended to build images for these machines with the appropriate build arguments (e.g., `--build-arg VLLM_CPU_DISABLE_AVX512=true`, `--build-arg VLLM_CPU_AVX512BF16=false`, or `--build-arg VLLM_CPU_AVX512VNNI=false`) to disable unsupported features. Please note that without `avx512f`, AVX2 will be used and this version is not recommended because it only has basic feature support.

# --8<-- [end:pre-built-images]
# --8<-- [start:build-image-from-source]
Expand All @@ -37,6 +37,7 @@ vLLM supports basic model inferencing and serving on x86 CPU platform, with data
docker build -f docker/Dockerfile.cpu \
--build-arg VLLM_CPU_AVX512BF16=false (default)|true \
--build-arg VLLM_CPU_AVX512VNNI=false (default)|true \
--build-arg VLLM_CPU_DISABLE_AVX512=false (default)|true \
--tag vllm-cpu-env \
--target vllm-openai .

Expand Down