Skip to content

v0.6.0-rc.3

@varungup90 varungup90 tagged this 03 Mar 19:09
* feat: add sglang gateway metrics and gateway dashboard (#1959)

* add more metrics
* pass label from the engine side
* chore: add grafana dashboard
* refactor the metrics to only expose one public method

Signed-off-by: chenyu.jiang <chenyu.jiang@bytedance.com>
Co-authored-by: chenyu.jiang <chenyu.jiang@bytedance.com>

* feat: add support for routing-profiles (#1944)

Signed-off-by: varungupta <varungup90@gmail.com>

* Feat: Support vllm new kvevent format (#1962)

* Feat: Support vllm new kvevent format

Signed-off-by: qiupengfei <qiupengfei@baidu.com>
Change-Id: I5aafd7fbb42c72e62ba6ac06065a790e46c3e9f9

* Fix: isSamePod is wrong & incr RouterInit timeout

Signed-off-by: qiupengfei <qiupengfei@baidu.com>
Change-Id: Ia495ac8f352d0e92872b5d1847c4ea6330909c6c

* Fix: gemini cr suggestion & unittest

Signed-off-by: qiupengfei <qiupengfei@baidu.com>
Change-Id: I7bf72cfaa964beb4729db943111db0113ecac184

* Fix: gofmt error

Signed-off-by: qiupengfei <qiupengfei@baidu.com>
Change-Id: I979001891d1bf506afd3699911e50ad046caf878

* Fix: parseBlockHashToInt64 should handle float64 and float32

Signed-off-by: qiupengfei <qiupengfei@baidu.com>
Change-Id: I26a889bba182538bd2692c81301047f8b881b2ea

---------

Signed-off-by: qiupengfei <qiupengfei@baidu.com>
Co-authored-by: qiupengfei <qiupengfei@baidu.com>

* feat: add queue for prometheus query (#1964)

Signed-off-by: chenyu.jiang <chenyu.jiang@bytedance.com>

* fix: update metric name for routing-algorithms (#1968)

Signed-off-by: varungupta <varungup90@gmail.com>

* fix: add shared path for the downloaded artifacts (#1972)

Signed-off-by: chenyu.jiang <chenyu.jiang@bytedance.com>

---------

Signed-off-by: chenyu.jiang <chenyu.jiang@bytedance.com>
Signed-off-by: varungupta <varungup90@gmail.com>
Signed-off-by: qiupengfei <qiupengfei@baidu.com>
Co-authored-by: Chenyu Jiang <38214590+scarlet25151@users.noreply.github.com>
Co-authored-by: chenyu.jiang <chenyu.jiang@bytedance.com>
Co-authored-by: penfree <15196366+penfree@users.noreply.github.com>
Co-authored-by: qiupengfei <qiupengfei@baidu.com>
Assets 2
Loading