@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 0b544e6476
Fork 0

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 10, 22:45 UTC

[Docs] Fix some snippets (#31378)

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

Harry Mellor committed Dec 26, 2025 at 12:47 UTC 0b544e6476eb88c3c011522c1feea6f16edf7022
15 files changed +20 -20
docs/cli/bench/latency.md
+1 -1
@@ -6,4 +6,4 @@
6
7 ## Arguments
8
9 ---8<-- "docs/argparse/bench_latency.inc.md"
9 +--8<-- "docs/generated/argparse/bench_latency.inc.md"
docs/cli/bench/serve.md
+1 -1
@@ -6,4 +6,4 @@
6
7 ## Arguments
8
9 ---8<-- "docs/argparse/bench_serve.inc.md"
9 +--8<-- "docs/generated/argparse/bench_serve.inc.md"
docs/cli/bench/sweep/plot.md
+1 -1
@@ -6,4 +6,4 @@
6
7 ## Arguments
8
9 ---8<-- "docs/argparse/bench_sweep_plot.inc.md"
9 +--8<-- "docs/generated/argparse/bench_sweep_plot.inc.md"
docs/cli/bench/sweep/plot_pareto.md
+1 -1
@@ -6,4 +6,4 @@
6
7 ## Arguments
8
9 ---8<-- "docs/argparse/bench_sweep_plot_pareto.inc.md"
9 +--8<-- "docs/generated/argparse/bench_sweep_plot_pareto.inc.md"
docs/cli/bench/sweep/serve.md
+1 -1
@@ -6,4 +6,4 @@
6
7 ## Arguments
8
9 ---8<-- "docs/argparse/bench_sweep_serve.inc.md"
9 +--8<-- "docs/generated/argparse/bench_sweep_serve.inc.md"
docs/cli/bench/sweep/serve_sla.md
+1 -1
@@ -6,4 +6,4 @@
6
7 ## Arguments
8
9 ---8<-- "docs/argparse/bench_sweep_serve_sla.inc.md"
9 +--8<-- "docs/generated/argparse/bench_sweep_serve_sla.inc.md"
docs/cli/bench/throughput.md
+1 -1
@@ -6,4 +6,4 @@
6
7 ## Arguments
8
9 ---8<-- "docs/argparse/bench_throughput.inc.md"
9 +--8<-- "docs/generated/argparse/bench_throughput.inc.md"
docs/cli/chat.md
+1 -1
@@ -2,4 +2,4 @@
2
3 ## Arguments
4
5 ---8<-- "docs/argparse/chat.inc.md"
5 +--8<-- "docs/generated/argparse/chat.inc.md"
docs/cli/complete.md
+1 -1
@@ -2,4 +2,4 @@
2
3 ## Arguments
4
5 ---8<-- "docs/argparse/complete.inc.md"
5 +--8<-- "docs/generated/argparse/complete.inc.md"
docs/cli/run-batch.md
+1 -1
@@ -6,4 +6,4 @@
6
7 ## Arguments
8
9 ---8<-- "docs/argparse/run-batch.inc.md"
9 +--8<-- "docs/generated/argparse/run-batch.inc.md"
docs/cli/serve.md
+1 -1
@@ -6,4 +6,4 @@
6
7 ## Arguments
8
9 ---8<-- "docs/argparse/serve.inc.md"
9 +--8<-- "docs/generated/argparse/serve.inc.md"
docs/configuration/engine_args.md
+2 -2
@@ -15,8 +15,8 @@ The engine argument classes, [EngineArgs][vllm.engine.arg_utils.EngineArgs] and
15
16 ## `EngineArgs`
17
18 ---8<-- "docs/argparse/engine_args.md"
18 +--8<-- "docs/generated/argparse/engine_args.inc.md"
19
20 ## `AsyncEngineArgs`
21
22 ---8<-- "docs/argparse/async_engine_args.md"
22 +--8<-- "docs/generated/argparse/async_engine_args.inc.md"
docs/mkdocs/hooks/generate_argparse.py
+1 -1
@@ -17,7 +17,7 @@ from pydantic_core import core_schema
17 logger = logging.getLogger("mkdocs")
18
19 ROOT_DIR = Path(__file__).parent.parent.parent.parent
20 -ARGPARSE_DOC_DIR = ROOT_DIR / "docs/argparse"
20 +ARGPARSE_DOC_DIR = ROOT_DIR / "docs/generated/argparse"
21
22 sys.path.insert(0, str(ROOT_DIR))
23
docs/mkdocs/hooks/generate_metrics.py
+3 -3
@@ -13,14 +13,14 @@ GENERATED_METRICS_DIR = DOCS_DIR / "generated" / "metrics"
13
14 # Files to scan for metric definitions - each will generate a separate table
15 METRIC_SOURCE_FILES = [
16 - {"path": "vllm/v1/metrics/loggers.py", "output": "general.md"},
16 + {"path": "vllm/v1/metrics/loggers.py", "output": "general.inc.md"},
17 {
18 "path": "vllm/v1/spec_decode/metrics.py",
19 - "output": "spec_decode.md",
19 + "output": "spec_decode.inc.md",
20 },
21 {
22 "path": "vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py",
23 - "output": "nixl_connector.md",
23 + "output": "nixl_connector.inc.md",
24 },
25 ]
26
docs/usage/metrics.md
+3 -3
@@ -35,15 +35,15 @@ The following metrics are exposed:
35
36 ## General Metrics
37
38 ---8<-- "docs/generated/metrics/general.md"
38 +--8<-- "docs/generated/metrics/general.inc.md"
39
40 ## Speculative Decoding Metrics
41
42 ---8<-- "docs/generated/metrics/spec_decode.md"
42 +--8<-- "docs/generated/metrics/spec_decode.inc.md"
43
44 ## NIXL KV Connector Metrics
45
46 ---8<-- "docs/generated/metrics/nixl_connector.md"
46 +--8<-- "docs/generated/metrics/nixl_connector.inc.md"
47
48 ## Deprecation Policy
49