xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-07 12:03:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

Moved numba from common requirements to cuda/rocm specific requirements (#14199)

Browse Source 
Signed-off-by: Nishidha Panpaliya <nishidha.panpaliya@partner.ibm.com>
This commit is contained in:
Nishidha 2025-03-05 09:55:00 +05:30 committed by GitHub
parent eb59b5a6cb
commit 5b143d33be
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
requirements-common.txt
View File

@ -1,7 +1,6 @@
psutil
sentencepiece # Required for LLaMA tokenizer.
numpy < 2.0.0
numba == 0.60.0 # v0.61 doesn't support Python 3.9. Required for N-gram speculative decoding.
requests >= 2.26.0
tqdm
blake3

2
requirements-cuda.txt
View File

@ -1,6 +1,8 @@
# Common dependencies
-r requirements-common.txt
numba == 0.60.0 # v0.61 doesn't support Python 3.9. Required for N-gram speculative decoding
# Dependencies for NVIDIA GPUs
ray[cgraph] >= 2.43.0 # Ray Compiled Graph, required for pipeline parallelism in V1.
torch == 2.5.1

4
requirements-rocm.txt
View File

@ -1,6 +1,8 @@
# Common dependencies
-r requirements-common.txt
numba == 0.60.0 # v0.61 doesn't support Python 3.9. Required for N-gram speculative decoding
# Dependencies for AMD GPUs
awscli
boto3
@ -11,4 +13,4 @@ peft
pytest-asyncio
tensorizer>=2.9.0
runai-model-streamer==0.11.0
runai-model-streamer-s3==0.11.0
runai-model-streamer-s3==0.11.0