biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Doc] Fix typo in documentation (#14783)

Browse Source 
Signed-off-by: yasu52 <tsuguro4649@gmail.com>
This commit is contained in:
yasu52
2025-03-13 20:33:09 -07:00
committed by GitHub
parent d47807ba08
commit 3fb17d26c8
13 changed files with 19 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/design/kernel/paged_attention.md
View File

@@ -419,7 +419,7 @@ List of `v_vec` for one thread
which is also `V_VEC_SIZE` elements from `logits`. Overall, with
multiple inner iterations, each warp will process one block of value
tokens. And with multiple outer iterations, the whole context value
tokens are processd
tokens are processed
```cpp
float accs[NUM_ROWS_PER_THREAD];

4
docs/source/design/v1/metrics.md
View File

@@ -13,7 +13,7 @@ Ensure the v1 LLM Engine exposes a superset of the metrics available in v0.
Metrics in vLLM can be categorized as follows:
1. Server-level metrics: these are global metrics that track the state and performance of the LLM engine. These are typically exposed as Gauges or Counters in Prometheus.
2. Request-level metrics: these are metrics that track the characteristics - e.g. size and timing - of individual requests. These are typically exposed as Histrograms in Prometheus, and are often the SLO that an SRE monitoring vLLM will be tracking.
2. Request-level metrics: these are metrics that track the characteristics - e.g. size and timing - of individual requests. These are typically exposed as Histograms in Prometheus, and are often the SLO that an SRE monitoring vLLM will be tracking.
The mental model is that the "Server-level Metrics" explain why the "Request-level Metrics" are what they are.
@@ -47,7 +47,7 @@ In v0, the following metrics are exposed via a Prometheus-compatible `/metrics`
- `vllm:tokens_total` (Counter)
- `vllm:iteration_tokens_total` (Histogram)
- `vllm:time_in_queue_requests` (Histogram)
- `vllm:model_forward_time_milliseconds` (Histogram
- `vllm:model_forward_time_milliseconds` (Histogram)
- `vllm:model_execute_time_milliseconds` (Histogram)
- `vllm:request_params_n` (Histogram)
- `vllm:request_params_max_tokens` (Histogram)