[WIP][XPU] upgrade torch-xpu to 2.12 (#42262)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com> Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
This commit is contained in:
@@ -203,7 +203,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
|
||||
uv pip install -r /workspace/vllm/requirements/xpu.txt && \
|
||||
uv pip install --no-build-isolation -r /workspace/vllm/requirements/test/xpu.txt && \
|
||||
uv pip uninstall triton triton-xpu && \
|
||||
uv pip install triton-xpu==3.7.0 && \
|
||||
uv pip install triton-xpu==3.7.1 && \
|
||||
uv pip uninstall oneccl oneccl-devel && \
|
||||
source /opt/intel/oneapi/setvars.sh --force && \
|
||||
source /opt/intel/oneapi/ccl/2021.15/env/vars.sh --force && \
|
||||
|
||||
@@ -41,12 +41,12 @@ pip install -v -r requirements/xpu.txt
|
||||
|
||||
```bash
|
||||
pip uninstall -y triton triton-xpu
|
||||
pip install triton-xpu==3.7.0 --extra-index-url https://download.pytorch.org/whl/xpu
|
||||
pip install triton-xpu==3.7.1 --extra-index-url https://download.pytorch.org/whl/xpu
|
||||
```
|
||||
|
||||
!!! note
|
||||
- `triton` (without suffix) is for NVIDIA GPUs only. On XPU, using it instead of `triton-xpu` can cause correctness or runtime issues.
|
||||
- For torch 2.11 (the version used in `requirements/xpu.txt`), the matching package is `triton-xpu==3.7.0`. 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).
|
||||
- For torch 2.12 (the version used in `requirements/xpu.txt`), the matching package is `triton-xpu==3.7.1`. 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).
|
||||
|
||||
- Finally, build and install vLLM XPU backend:
|
||||
|
||||
|
||||
@@ -31,7 +31,7 @@ schemathesis
|
||||
jiwer
|
||||
bm25s
|
||||
pystemmer
|
||||
mteb[bm25s]
|
||||
mteb[bm25s]>=2, <3 # required for mteb test
|
||||
num2words
|
||||
pqdm
|
||||
|
||||
|
||||
@@ -646,7 +646,7 @@ tokenizers==0.22.2
|
||||
# via
|
||||
# -c requirements/common.txt
|
||||
# transformers
|
||||
torch==2.11.0+xpu
|
||||
torch==2.12.0+xpu
|
||||
# via
|
||||
# -c requirements/xpu.txt
|
||||
# accelerate
|
||||
@@ -654,7 +654,7 @@ torch==2.11.0+xpu
|
||||
# sentence-transformers
|
||||
# timm
|
||||
# torchvision
|
||||
torchvision==0.26.0+xpu
|
||||
torchvision==0.27.0+xpu
|
||||
# via timm
|
||||
tqdm==4.67.3
|
||||
# via
|
||||
@@ -672,7 +672,7 @@ transformers==5.5.3
|
||||
# via
|
||||
# -c requirements/common.txt
|
||||
# sentence-transformers
|
||||
triton-xpu==3.7.0
|
||||
triton-xpu==3.7.1
|
||||
# via torch
|
||||
typepy==1.3.4
|
||||
# via
|
||||
|
||||
@@ -12,9 +12,9 @@ jinja2>=3.1.6
|
||||
datasets # for benchmark scripts
|
||||
numba == 0.65.0 # Required for N-gram speculative decoding
|
||||
--extra-index-url=https://download.pytorch.org/whl/xpu
|
||||
torch==2.11.0
|
||||
torch==2.12.0
|
||||
torchaudio
|
||||
torchvision
|
||||
|
||||
auto_round_lib>=0.13.0
|
||||
vllm_xpu_kernels @ https://github.com/vllm-project/vllm-xpu-kernels/releases/download/v0.1.9/vllm_xpu_kernels-0.1.9-cp38-abi3-manylinux_2_28_x86_64.whl
|
||||
vllm_xpu_kernels @ https://github.com/vllm-project/vllm-xpu-kernels/releases/download/v0.1.9.1/vllm_xpu_kernels-0.1.9.1-cp38-abi3-manylinux_2_28_x86_64.whl
|
||||
|
||||
Reference in New Issue
Block a user