obscura/vllm
2
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2026-06-06 00:16:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

[NVIDIA] Add sm_110 (Jetson Thor) to CUDA 13.0 build targets (#39233)

Browse Source
This commit is contained in:
Johnny
2026-04-23 21:42:14 +02:00
committed by GitHub
parent 1b1c01de39
commit 7f95a66cbf
4 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docker/Dockerfile
+2 -2
View File
@@ -188,7 +188,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
# Explicitly set the list to avoid issues with torch 2.2
# See https://github.com/pytorch/pytorch/pull/123243
# From versions.json: .torch.cuda_arch_list
ARG torch_cuda_arch_list='7.5 8.0 8.6 8.9 9.0 10.0 12.0+PTX'
ARG torch_cuda_arch_list='7.5 8.0 8.6 8.9 9.0 10.0 11.0 12.0+PTX'
ENV TORCH_CUDA_ARCH_LIST=${torch_cuda_arch_list}
#################### BUILD BASE IMAGE ####################
@@ -765,7 +765,7 @@ ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
ENV UV_HTTP_TIMEOUT=500
# install kv_connectors if requested
ARG torch_cuda_arch_list='7.5 8.0 8.6 8.9 9.0 10.0 12.0+PTX'
ARG torch_cuda_arch_list='7.5 8.0 8.6 8.9 9.0 10.0 11.0 12.0+PTX'
ENV TORCH_CUDA_ARCH_LIST=${torch_cuda_arch_list}
RUN --mount=type=cache,target=/root/.cache/uv \
--mount=type=bind,source=requirements/kv_connectors.txt,target=/tmp/kv_connectors.txt,ro \
docker/docker-bake.hcl
+1 -1
View File
@@ -20,7 +20,7 @@ variable "NVCC_THREADS" {
}
variable "TORCH_CUDA_ARCH_LIST" {
default = "8.0 8.9 9.0 10.0"
default = "8.0 8.9 9.0 10.0 11.0 12.0"
}
variable "COMMIT" {
docker/versions.json
+1 -1
View File
@@ -32,7 +32,7 @@
"default": "false"
},
"TORCH_CUDA_ARCH_LIST": {
"default": "7.5 8.0 8.6 8.9 9.0 10.0 12.0+PTX"
"default": "7.5 8.0 8.6 8.9 9.0 10.0 11.0 12.0+PTX"
},
"MAX_JOBS": {
"default": "2"
tools/flashinfer-build.sh
+1 -1
View File
@@ -35,7 +35,7 @@ elif [[ "${CUDA_VERSION}" == 12.[8-9]* ]]; then
FI_TORCH_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a 10.3a 12.0"
else
# CUDA 13.0+
FI_TORCH_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0f 12.0"
FI_TORCH_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0f 11.0 12.0f"
fi
echo "🏗️ Building FlashInfer AOT for arches: ${FI_TORCH_CUDA_ARCH_LIST}"