kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-16 07:53:55 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[None][infra] Pin the torchao version (#11444)

Browse Source 
Signed-off-by: qqiao <qqiao@nvidia.com>
This commit is contained in:
Emma Qiao 2026-02-11 17:40:40 +08:00 committed by GitHub
parent e8b860965b
commit eed9c16560
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
requirements.txt
View File

@ -77,7 +77,7 @@ partial_json_parser
apache-tvm-ffi==0.1.6 # used for reduce nvidia-cutlass-dsl host overhead
torch-c-dlpack-ext==0.1.3 # used for reduce nvidia-cutlass-dsl host overhead, optional package for improved torch tensor calling perf
mistral-common==1.8.6
torchao>=0.14.1
torchao>=0.14.1,<0.16.0
cuda-core
llist
cuda-tile>=1.0.1