Skip to content

Actions: llm-d/llm-d-inference-sim

Actions

Prow github actions

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
prow-github.yml
184 workflow runs
184 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Support OpenAI error response structure Prow github actions #34: Issue comment #135 (comment) created by irar2
7s
7s
feat: generate response length based on a histogram when max_tokens is defined in the request Prow github actions #33: Issue comment #169 (comment) created by shmuelk
11s
11s
Add failure injection mode to simulator Prow github actions #32: Issue comment #131 (comment) created by irar2
9s
9s
Add waiting loras list to loraInfo metrics Prow github actions #31: Issue comment #175 (comment) created by mayabar
6s
6s
Add failure injection mode to simulator Prow github actions #30: Issue comment #131 (comment) created by mayabar
5s
5s
Add failure injection mode to simulator Prow github actions #29: Issue comment #131 (comment) created by irar2
7s
7s
Support OpenAI error response structure Prow github actions #28: Issue comment #135 (comment) created by irar2
7s
7s
Use dynamic ports in zmq tests Prow github actions #27: Issue comment #170 (comment) created by irar2
6s
6s
Add failure injection mode to simulator Prow github actions #26: Issue comment #131 (comment) created by irar2
6s
6s
Use dynamic ports in zmq tests Prow github actions #25: Issue comment #170 (comment) created by pancak3
9s
9s
Implement waiting loras metrics Prow github actions #24: Issue comment #140 (comment) created by mayabar
8s
8s
Remove rerun on comment action Prow github actions #23: Issue comment #174 (comment) created by mayabar
6s
6s
Use channels for metrics updates, added metrics tests Prow github actions #22: Issue comment #171 (comment) created by mayabar
7s
7s
Use dynamic ports in zmq tests Prow github actions #21: Issue comment #170 (comment) created by irar2
8s
8s
Use channels for metrics updates, added metrics tests Prow github actions #20: Issue comment #171 (comment) created by mayabar
10s
10s
Add failure injection mode to simulator Prow github actions #19: Issue comment #131 (comment) created by smarunich
9s
9s
Add failure injection mode to simulator Prow github actions #18: Issue comment #131 (comment) created by smarunich
8s
8s
Change time-to-first-token parameter to be based on number of request tokens #137 Prow github actions #17: Issue comment #165 (comment) created by mayabar
5s
5s
Enhance calculation of tokens number in response based on request's max_tokens parameter Prow github actions #16: Issue comment #136 (comment) created by mayabar
7s
7s
Fix: Rand generator is not set in a test suite which result in accessing nil pointer during runtime if run the only test suite Prow github actions #15: Issue comment #166 (comment) created by irar2
7s
7s
Enhance calculation of tokens number in response based on request's max_tokens parameter Prow github actions #14: Issue comment #136 (comment) created by mayabar
7s
7s
Implement waiting loras metrics Prow github actions #13: Issue comment #140 (comment) created by mayabar
6s
6s
Remvoe unnecessary deferal of server close Prow github actions #12: Issue comment #162 (comment) created by irar2
6s
6s
Cast bounds type in tests to func def: latency, interToken, and timeToFirst (to int) Prow github actions #11: Issue comment #163 (comment) created by irar2
13s
13s
Show final config in simulaor default logger at Info lvel Prow github actions #10: Issue comment #154 (comment) created by irar2
9s
9s