mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2026-01-23 16:14:37 +08:00
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
parent
f4b76056ee
commit
b34e8775a3
@ -119,6 +119,7 @@ FROM base AS vllm-test-deps
|
||||
|
||||
WORKDIR /workspace/vllm
|
||||
|
||||
# TODO: Update to 2.9.0 when there is a new build for intel_extension_for_pytorch for that version
|
||||
RUN --mount=type=bind,src=requirements/test.in,target=requirements/test.in \
|
||||
cp requirements/test.in requirements/cpu-test.in && \
|
||||
sed -i '/mamba_ssm/d' requirements/cpu-test.in && \
|
||||
@ -131,6 +132,9 @@ RUN --mount=type=bind,src=requirements/test.in,target=requirements/test.in \
|
||||
esac; \
|
||||
}; \
|
||||
remove_packages_not_supported_on_aarch64 && \
|
||||
sed -i 's/^torch==.*/torch==2.8.0/g' requirements/cpu-test.in && \
|
||||
sed -i 's/torchaudio.*/torchaudio/g' requirements/cpu-test.in && \
|
||||
sed -i 's/torchvision.*/torchvision/g' requirements/cpu-test.in && \
|
||||
uv pip compile requirements/cpu-test.in -o requirements/cpu-test.txt --index-strategy unsafe-best-match --torch-backend cpu
|
||||
|
||||
RUN --mount=type=cache,target=/root/.cache/uv \
|
||||
|
||||
@ -4,9 +4,9 @@ packaging>=24.2
|
||||
setuptools>=77.0.3,<81.0.0
|
||||
setuptools-scm>=8
|
||||
--extra-index-url https://download.pytorch.org/whl/cpu
|
||||
torch==2.9.0+cpu; platform_machine == "x86_64" or platform_machine == "s390x"
|
||||
torch==2.8.0+cpu; platform_machine == "x86_64" or platform_machine == "s390x"
|
||||
torch==2.9.0; platform_system == "Darwin"
|
||||
torch==2.9.0; platform_machine == "ppc64le" or platform_machine == "aarch64"
|
||||
torch==2.8.0; platform_machine == "ppc64le" or platform_machine == "aarch64"
|
||||
scons; platform_machine == "aarch64" # needed to build Arm Compute Library (ACL)
|
||||
wheel
|
||||
jinja2>=3.1.6
|
||||
|
||||
@ -7,17 +7,17 @@ numba == 0.61.2; platform_machine != "s390x" # Required for N-gram speculative d
|
||||
packaging>=24.2
|
||||
setuptools>=77.0.3,<81.0.0
|
||||
--extra-index-url https://download.pytorch.org/whl/cpu
|
||||
torch==2.9.0+cpu; platform_machine == "x86_64" or platform_machine == "s390x"
|
||||
torch==2.8.0+cpu; platform_machine == "x86_64" or platform_machine == "s390x"
|
||||
torch==2.9.0; platform_system == "Darwin"
|
||||
torch==2.9.0; platform_machine == "ppc64le" or platform_machine == "aarch64"
|
||||
torch==2.8.0; platform_machine == "ppc64le" or platform_machine == "aarch64"
|
||||
|
||||
# required for the image processor of minicpm-o-2_6, this must be updated alongside torch
|
||||
torchaudio; platform_machine != "ppc64le" and platform_machine != "s390x"
|
||||
torchaudio==2.9.0; platform_machine == "ppc64le"
|
||||
torchaudio==2.8.0; platform_machine == "ppc64le"
|
||||
|
||||
# required for the image processor of phi3v, this must be updated alongside torch
|
||||
torchvision; platform_machine != "ppc64le" and platform_machine != "s390x"
|
||||
torchvision==0.24.0; platform_machine == "ppc64le"
|
||||
torchvision==0.23.0; platform_machine == "ppc64le"
|
||||
datasets # for benchmark scripts
|
||||
|
||||
# Intel Extension for PyTorch, only for x86_64 CPUs
|
||||
|
||||
@ -1123,14 +1123,14 @@ class Qwen3LLMModel(Qwen3Model):
|
||||
assert intermediate_tensors is not None
|
||||
hidden_states = intermediate_tensors["hidden_states"]
|
||||
residual = intermediate_tensors["residual"]
|
||||
|
||||
|
||||
aux_hidden_states = []
|
||||
for layer_idx, layer in islice(
|
||||
enumerate(self.layers), self.start_layer, self.end_layer
|
||||
):
|
||||
if layer_idx in self.aux_hidden_state_layers:
|
||||
aux_hidden_states.append(hidden_states + residual)
|
||||
|
||||
|
||||
hidden_states, residual = layer(
|
||||
positions,
|
||||
hidden_states,
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user