A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 03:00 UTC
[Misc] Upgrade triton to 2.2.0 (#4061)
Roy committed
Apr 15, 2024 at 08:43 UTC
8db1bf32f8924403c6a845b5ce71ba0f14beb038
2 files changed
+1
-2
requirements-cpu.txt
+1
-1
@@ -3,4 +3,4 @@
3
4
# Dependencies for x86_64 CPUs
5
torch == 2.2.1+cpu
6
-triton >= 2.1.0 # FIXME(woosuk): This is a hack to avoid import error.
\ No newline at end of file
6
+triton >= 2.2.0 # FIXME(woosuk): This is a hack to avoid import error.
\ No newline at end of file
requirements-cuda.txt
-1
@@ -7,4 +7,3 @@ pynvml == 11.5.0
7
vllm-nccl-cu12>=2.18,<2.19 # for downloading nccl library
8
torch == 2.2.1
9
xformers == 0.0.25 # Requires PyTorch 2.2.1
10
-triton >= 2.1.0