From 2e0d2d4c18f6987a4e64801105ba5765b52d4111 Mon Sep 17 00:00:00 2001 From: loading66 <102725781+loading66@users.noreply.github.com> Date: Thu, 21 May 2026 19:08:10 +0800 Subject: [PATCH] [NPU][DOCS]Add best practice and benchmark result parameter description (#25875) --- .../ascend-npus/ascend_npu_best_practice.mdx | 530 +++++++++++++++++- .../ascend_npu_performance_testing.mdx | 105 ++++ 2 files changed, 622 insertions(+), 13 deletions(-) diff --git a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_best_practice.mdx b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_best_practice.mdx index 2617008cb..647871e03 100644 --- a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_best_practice.mdx +++ b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_best_practice.mdx @@ -264,7 +264,7 @@ you encounter issues or have any questions, please [open an issue](https://githu
| Parameter | +Description | +
|---|---|
Backend |
+ The serving backend under test (e.g., sglang, vllm). |
+
Traffic request rate |
+ Request generation rate in req/s. inf means maximum rate (concurrency-bounded). trace indicates trace timestamp mode. A fixed value enforces constant inter-arrival time. |
+
Max request concurrency |
+ Maximum number of concurrent requests from the client side. Displays not set when unspecified. |
+
| Parameter | +Description | +Format Specification | +
|---|---|---|
Successful requests | Total number of successfully completed requests (HTTP 200, no generation errors). | Integer, no decimal places |
Benchmark duration (s) | Total elapsed time from first request sent to last response fully received (seconds). | 2 decimal places |
Total input tokens | Total number of input (prompt) tokens across all requests, counted by server-side tokenizer. | Integer, no decimal places |
Total input text tokens | Same as Total input tokens. For multimodal inputs, this may differ. | Integer, no decimal places |
Total generated tokens | Total number of output tokens actually generated by the server (server-side tokenizer count). | Integer, no decimal places |
Total generated tokens (retokenized) | Output text re-tokenized by the client using its own tokenizer. A large discrepancy indicates tokenizer mismatch or special tokens in output. | Integer, no decimal places |
Request throughput (req/s) | Number of successful requests processed per second. Formula: Successful requests / Benchmark duration (s). | 2 decimal places |
Input token throughput (tok/s) | Number of input tokens processed per second. Formula: Total input tokens / Benchmark duration (s). | 2 decimal places |
Output token throughput (tok/s) | Number of output tokens generated per second. Formula: Total generated tokens / Benchmark duration (s). | 2 decimal places |
Peak output token throughput (tok/s) | Observed instantaneous peak output token generation rate during the test (computed over a sliding window). | 2 decimal places |
Peak concurrent requests | Maximum number of requests being processed simultaneously on the server side. May exceed client-side Max request concurrency due to queueing. | Integer, no decimal places |
Total token throughput (tok/s) | Sum of input and output token throughputs. Formula: Input token throughput + Output token throughput. | 2 decimal places |
Concurrency | Average number of concurrent requests during the test (Little's Law). Formula: Sum of all E2E latencies / Benchmark duration. | 2 decimal places |
| Statistic | Description | Format |
|---|---|---|
Mean E2E Latency (ms) | Arithmetic mean | 2 decimal places |
Median E2E Latency (ms) | 50th percentile | 2 decimal places |
P90 E2E Latency (ms) | 90th percentile (90% of requests have latency ≤ this value) | 2 decimal places |
P99 E2E Latency (ms) | 99th percentile | 2 decimal places |
| Statistic | Description | Format |
|---|---|---|
Mean TTFT (ms) | Arithmetic mean | 2 decimal places |
Median TTFT (ms) | 50th percentile | 2 decimal places |
P99 TTFT (ms) | 99th percentile | 2 decimal places |
(E2E Latency - TTFT) / (Number of output tokens - 1)
+
+| Statistic | Description | Format |
|---|---|---|
Mean TPOT (ms) | Arithmetic mean | 2 decimal places |
Median TPOT (ms) | 50th percentile | 2 decimal places |
P99 TPOT (ms) | 99th percentile | 2 decimal places |
| Statistic | Description | Format |
|---|---|---|
Mean ITL (ms) | Average inter-token interval | 2 decimal places |
Median ITL (ms) | 50th percentile inter-token interval | 2 decimal places |
P95 ITL (ms) | 95th percentile (used to detect stalls) | 2 decimal places |
P99 ITL (ms) | 99th percentile | 2 decimal places |
Max ITL (ms) | Maximum observed inter-token interval; useful for identifying severe blocking events | 2 decimal places |