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, 06:45 UTC
fix typo in getenv call (#1972)
Daya Khudia committed
Dec 7, 2023 at 16:04 UTC
c8e7eb1eb3e3862cde4f7c27952d2eb9104ef416
1 file changed
+1
-1
setup.py
+1
-1
@@ -138,7 +138,7 @@ for capability in compute_capabilities:
138
139
# Use NVCC threads to parallelize the build.
140
if nvcc_cuda_version >= Version("11.2"):
141
- nvcc_threads = int(os.getenv("NVCC_THREADS"), 8)
141
+ nvcc_threads = int(os.getenv("NVCC_THREADS", 8))
142
num_threads = min(os.cpu_count(), nvcc_threads)
143
NVCC_FLAGS += ["--threads", str(num_threads)]
144