[Docs] Fix some snippets (#31378)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

docs/cli/bench/latency.md

@@ -6,4 +6,4 @@
 
 ## Arguments
 
---8<-- "docs/argparse/bench_latency.inc.md"
+--8<-- "docs/generated/argparse/bench_latency.inc.md"

docs/cli/bench/serve.md

@@ -6,4 +6,4 @@
 
 ## Arguments
 
---8<-- "docs/argparse/bench_serve.inc.md"
+--8<-- "docs/generated/argparse/bench_serve.inc.md"

docs/cli/bench/sweep/plot.md

@@ -6,4 +6,4 @@
 
 ## Arguments
 
---8<-- "docs/argparse/bench_sweep_plot.inc.md"
+--8<-- "docs/generated/argparse/bench_sweep_plot.inc.md"

docs/cli/bench/sweep/plot_pareto.md

@@ -6,4 +6,4 @@
 
 ## Arguments
 
---8<-- "docs/argparse/bench_sweep_plot_pareto.inc.md"
+--8<-- "docs/generated/argparse/bench_sweep_plot_pareto.inc.md"

docs/cli/bench/sweep/serve.md

@@ -6,4 +6,4 @@
 
 ## Arguments
 
---8<-- "docs/argparse/bench_sweep_serve.inc.md"
+--8<-- "docs/generated/argparse/bench_sweep_serve.inc.md"

docs/cli/bench/sweep/serve_sla.md

@@ -6,4 +6,4 @@
 
 ## Arguments
 
---8<-- "docs/argparse/bench_sweep_serve_sla.inc.md"
+--8<-- "docs/generated/argparse/bench_sweep_serve_sla.inc.md"

docs/cli/bench/throughput.md

@@ -6,4 +6,4 @@
 
 ## Arguments
 
---8<-- "docs/argparse/bench_throughput.inc.md"
+--8<-- "docs/generated/argparse/bench_throughput.inc.md"

docs/cli/chat.md

@@ -2,4 +2,4 @@
 
 ## Arguments
 
---8<-- "docs/argparse/chat.inc.md"
+--8<-- "docs/generated/argparse/chat.inc.md"

docs/cli/complete.md

@@ -2,4 +2,4 @@
 
 ## Arguments
 
---8<-- "docs/argparse/complete.inc.md"
+--8<-- "docs/generated/argparse/complete.inc.md"

docs/cli/run-batch.md

@@ -6,4 +6,4 @@
 
 ## Arguments
 
---8<-- "docs/argparse/run-batch.inc.md"
+--8<-- "docs/generated/argparse/run-batch.inc.md"

docs/cli/serve.md

@@ -6,4 +6,4 @@
 
 ## Arguments
 
---8<-- "docs/argparse/serve.inc.md"
+--8<-- "docs/generated/argparse/serve.inc.md"

docs/configuration/engine_args.md

@@ -15,8 +15,8 @@ The engine argument classes, [EngineArgs][vllm.engine.arg_utils.EngineArgs] and
 
 ## `EngineArgs`
 
---8<-- "docs/argparse/engine_args.md"
+--8<-- "docs/generated/argparse/engine_args.inc.md"
 
 ## `AsyncEngineArgs`
 
---8<-- "docs/argparse/async_engine_args.md"
+--8<-- "docs/generated/argparse/async_engine_args.inc.md"

docs/mkdocs/hooks/generate_argparse.py

@@ -17,7 +17,7 @@ from pydantic_core import core_schema
 logger = logging.getLogger("mkdocs")
 
 ROOT_DIR = Path(__file__).parent.parent.parent.parent
-ARGPARSE_DOC_DIR = ROOT_DIR / "docs/argparse"
+ARGPARSE_DOC_DIR = ROOT_DIR / "docs/generated/argparse"
 
 sys.path.insert(0, str(ROOT_DIR))
 

docs/mkdocs/hooks/generate_metrics.py

@@ -13,14 +13,14 @@ GENERATED_METRICS_DIR = DOCS_DIR / "generated" / "metrics"
 
 # Files to scan for metric definitions - each will generate a separate table
 METRIC_SOURCE_FILES = [
-    {"path": "vllm/v1/metrics/loggers.py", "output": "general.md"},
+    {"path": "vllm/v1/metrics/loggers.py", "output": "general.inc.md"},
     {
         "path": "vllm/v1/spec_decode/metrics.py",
-        "output": "spec_decode.md",
+        "output": "spec_decode.inc.md",
     },
     {
         "path": "vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py",
-        "output": "nixl_connector.md",
+        "output": "nixl_connector.inc.md",
     },
 ]
 

docs/usage/metrics.md

@@ -35,15 +35,15 @@ The following metrics are exposed:
 
 ## General Metrics
 
---8<-- "docs/generated/metrics/general.md"
+--8<-- "docs/generated/metrics/general.inc.md"
 
 ## Speculative Decoding Metrics
 
---8<-- "docs/generated/metrics/spec_decode.md"
+--8<-- "docs/generated/metrics/spec_decode.inc.md"
 
 ## NIXL KV Connector Metrics
 
---8<-- "docs/generated/metrics/nixl_connector.md"
+--8<-- "docs/generated/metrics/nixl_connector.inc.md"
 
 ## Deprecation Policy