[macOS][CPU][Installation] Fix the broken installation of vllm 0.24.0 in macos + cpu (#47457)
Signed-off-by: Ranran Haoran Zhang <ranranhaoranzhang@gmail.com>
Ranran committed
Jul 6, 2026 at 10:59 UTC
3ee9eea9284c4fbe71459dec07063244e1b0ec75
1 file changed
+1
-1
requirements/cuda.txt
+1
-1
@@ -25,7 +25,7 @@ nvidia-cutlass-dsl[cu13]==4.5.2
25
quack-kernels>=0.3.3
26
27
# Tokenspeed_MLA for faster mla with spec decode
28
-tokenspeed-mla==0.1.2
28
+tokenspeed-mla==0.1.2; platform_system == "Linux"
29
30
# Humming kernels for quantization gemm
31
humming-kernels[cu13]==0.1.6