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 7, 01:30 UTC
[XPU][Doc] update xpu document about triton dependency/conflict issue. (#36301)
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Kunshang Ji committed
Mar 9, 2026 at 10:09 UTC
fde4771bbda69f86a58eace1447f3ab5e369b63d
1 file changed
+14
-1
docs/getting_started/installation/gpu.xpu.inc.md
+14
-1
@@ -35,7 +35,20 @@ pip install --upgrade pip
35
pip install -v -r requirements/xpu.txt
36
```
37
38
-- Then, build and install vLLM XPU backend:
38
+- Then, install the correct Triton package for Intel XPU.
39
+
40
+ The default `triton` package (for NVIDIA GPUs) may be installed as a transitive dependency (e.g., via `xgrammar`). For Intel XPU, you must replace it with `triton-xpu`:
41
+
42
+ ```bash
43
+ pip uninstall -y triton triton-xpu
44
+ pip install triton-xpu==3.6.0 --extra-index-url https://download.pytorch.org/whl/xpu
45
+ ```
46
+
47
+ !!! note
48
+ - `triton` (without suffix) is for NVIDIA GPUs only. On XPU, using it instead of `triton-xpu` can cause correctness or runtime issues.
49
+ - For torch 2.10 (the version used in `requirements/xpu.txt`), the matching package is `triton-xpu==3.6.0`. If you use a different version of torch, check the corresponding `triton-xpu` version in [docker/Dockerfile.xpu](https://github.com/vllm-project/vllm/blob/main/docker/Dockerfile.xpu).
50
+
51
+- Finally, build and install vLLM XPU backend:
52
53
```bash
54
VLLM_TARGET_DEVICE=xpu pip install --no-build-isolation -e . -v