|
|
@@ -16,7 +16,7 @@ services:
|
|
|
# --enable-torch-compile # You can also enable torch.compile to accelerate inference speed by approximately 15%
|
|
|
# --dp-size 2 # If using multiple GPUs, increase throughput using sglang's multi-GPU parallel mode
|
|
|
# --tp-size 2 # If you have more than one GPU, you can expand available VRAM using tensor parallelism (TP) mode.
|
|
|
- # --mem-fraction-static 0.5 # If running on a single GPU and encountering VRAM shortage, reduce the KV cache size by this parameter, If VRAM issues persist, try lowering it further to `0.4` or below.
|
|
|
+ # --mem-fraction-static 0.5 # If running on a single GPU and encountering VRAM shortage, reduce the KV cache size by this parameter, if VRAM issues persist, try lowering it further to `0.4` or below.
|
|
|
ulimits:
|
|
|
memlock: -1
|
|
|
stack: 67108864
|