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 14, 05:30 UTC
[gpt-oss] Add openai-harmony as default dependency (#22332)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu> Co-authored-by: LiuXiaoxuanPKU <lilyliupku@gmail.com> Co-authored-by: simon-mo <xmo@berkeley.edu> Co-authored-by: Chen Zhang <zhangch99@outlook.com> Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com> Co-authored-by: Minseok Lee <47620120+minseokl@users.noreply.github.com> Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Woosuk Kwon committed
Aug 6, 2025 at 00:10 UTC
134a8ee8fdbcbb838a54911fd2b129f2ceda0f17
1 file changed
+1
requirements/common.txt
+1
@@ -49,3 +49,4 @@ ninja # Required for xgrammar, rocm, tpu, xpu
49
pybase64 # fast base64 implementation
50
cbor2 # Required for cross-language serialization of hashable objects
51
setproctitle # Used to set process names for better debugging and monitoring
52
+openai-harmony >= 0.0.3 # Required for gpt-oss