Skip to content

fix: make doctest examples self-contained #577

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ganeshku1 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: make doctest examples self-contained #577

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 3 additions & 10 deletions docs/benchmark_modes/trace_replay.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,7 @@ Example entry:

## Profile using a Custom Trace File

Create a trace file with timing information:
Create a trace file with timing information and run AIPerf:

<!-- aiperf-run-vllm-default-openai-endpoint-server -->
```bash
Expand All @@ -67,12 +67,7 @@ cat > custom_trace.jsonl << 'EOF'
{"timestamp": 10535, "input_length": 672, "output_length": 26, "hash_ids": [0, 3, 4, 5]}
{"timestamp": 27482, "input_length": 655, "output_length": 52, "hash_ids": [0, 6, 7]}
EOF
```
<!-- /aiperf-run-vllm-default-openai-endpoint-server -->
Run AIPerf with the trace file:

<!-- aiperf-run-vllm-default-openai-endpoint-server -->
```bash
aiperf profile \
--model Qwen/Qwen3-0.6B \
--endpoint-type chat \
Expand All @@ -93,11 +88,9 @@ For real-world benchmarking, use the FAST25 production trace data from the Moonc
<!-- aiperf-run-vllm-default-openai-endpoint-server -->
```bash
# Download the Mooncake trace data
curl -o mooncake_trace.jsonl https://raw.githubusercontent.com/kvcache-ai/Mooncake/refs/heads/main/FAST25-release/arxiv-trace/mooncake_trace.jsonl

curl -L -o mooncake_trace.jsonl https://raw.githubusercontent.com/kvcache-ai/Mooncake/refs/heads/main/FAST25-release/arxiv-trace/mooncake_trace.jsonl && \
# Create a subset for quick testing
head -n 10 mooncake_trace.jsonl > mooncake_trace_short.jsonl

head -n 10 mooncake_trace.jsonl > mooncake_trace_short.jsonl && \
# Run the trace replay
aiperf profile \
--model Qwen/Qwen3-0.6B \
Expand Down
16 changes: 15 additions & 1 deletion docs/tutorials/fixed-schedule.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,21 @@ Execute only a portion of the schedule using start and end offsets:

<!-- aiperf-run-vllm-default-openai-endpoint-server -->
```bash
# Execute schedule from 2s to 6s window
# Create a fixed schedule with precise timing
cat > precise_schedule.jsonl << 'EOF'
{"timestamp": 0, "input_length": 100, "hash_ids": [3001]}
{"timestamp": 500, "input_length": 200, "hash_ids": [3002]}
{"timestamp": 750, "input_length": 150, "hash_ids": [3003]}
{"timestamp": 1000, "input_length": 300, "hash_ids": [3004]}
{"timestamp": 1250, "input_length": 180, "hash_ids": [3005]}
{"timestamp": 2000, "input_length": 400, "hash_ids": [3006]}
{"timestamp": 2500, "input_length": 250, "hash_ids": [3007]}
{"timestamp": 3000, "input_length": 350, "hash_ids": [3008]}
{"timestamp": 4000, "input_length": 500, "hash_ids": [3009]}
{"timestamp": 5000, "input_length": 600, "hash_ids": [3010, 3050]}
EOF

# Execute schedule from 2s to 4s window
aiperf profile \
--model Qwen/Qwen3-0.6B \
--endpoint-type chat \
Expand Down