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 4, 00:00 UTC
[Docs] Fix broken local links (#42160)
Signed-off-by: Ethan Feng <ethan.fengch@gmail.com>
Ethan Feng committed
May 10, 2026 at 16:15 UTC
a2c9d548d756f300fd5218d95d57414949a36b91
2 files changed
+2
-2
docs/benchmarking/cli.md
+1
-1
@@ -132,7 +132,7 @@ The generated timeline is an interactive visualization in the form of an HTML fi
132
133
Example output:
134
135
-<iframe src="../../assets/contributing/vllm_bench_serve_timeline.html" width="100%" height="600" frameborder="0"></iframe>
135
+<iframe src="../assets/contributing/vllm_bench_serve_timeline.html" width="100%" height="600" frameborder="0"></iframe>
136
137
##### Dataset statistics
138
tests/v1/ec_connector/integration/README.md
+1
-1
@@ -13,7 +13,7 @@ The test ensures that disaggregated encoding produces **identical** outputs to t
13
14
Note that currently PD disaggregation set up may give slightly different results from a single instance. Therefore, we need the result from 1P+1D as the baseline for 1E+1P+1D
15
16
-Please refer to [Disaggregated Encoder Feature](../../../docs/features/disagg_encoder.md) for the detailed explanation for the EPD features.
16
+Please refer to [Disaggregated Encoder Feature](../../../../docs/features/disagg_encoder.md) for the detailed explanation for the EPD features.
17
18
## Files
19