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 15, 13:30 UTC
[Doc] Remove unnecessary V1 flag (#16924)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Apr 22, 2025 at 09:04 UTC
29f395c97ca5c0e9e077c6166efee4b5ff948d1c
1 file changed
+2
-2
docs/source/design/v1/torch_compile.md
+2
-2
@@ -99,7 +99,7 @@ This time, Inductor compilation is completely bypassed, and we will load from di
99
100
The above example just uses Inductor to compile for a general shape (i.e. symbolic shape). We can also use Inductor to compile for some of the specific shapes, for example:
101
102
-`VLLM_USE_V1=1 vllm serve meta-llama/Llama-3.2-1B --compilation_config "{'compile_sizes': [1, 2, 4, 8]}"`
102
+`vllm serve meta-llama/Llama-3.2-1B --compilation_config "{'compile_sizes': [1, 2, 4, 8]}"`
103
104
Then it will also compile a specific kernel just for batch size `1, 2, 4, 8`. At this time, all of the shapes in the computation graph are static and known, and we will turn on auto-tuning to tune for max performance. This can be slow when you run it for the first time, but the next time you run it, we can directly bypass the tuning and run the tuned kernel.
105
@@ -134,6 +134,6 @@ The cudagraphs are captured and managed by the compiler backend, and replayed wh
134
135
By default, vLLM will try to determine a set of sizes to capture cudagraph. You can also override it using the config `cudagraph_capture_sizes`:
136
137
-`VLLM_USE_V1=1 vllm serve meta-llama/Llama-3.2-1B --compilation-config "{'cudagraph_capture_sizes': [1, 2, 4, 8]}"`
137
+`vllm serve meta-llama/Llama-3.2-1B --compilation-config "{'cudagraph_capture_sizes': [1, 2, 4, 8]}"`
138
139
Then it will only capture cudagraph for the specified sizes. It can be useful to have fine-grained control over the cudagraph capture.