Skip to content

Commit 37af6d1

Browse files
Update kimik2.5-int4-h200-vllm vLLM image to v0.21.0
Ref #1154 Co-authored-by: Klaud Cold <Klaud-Cold@users.noreply.github.com>
1 parent 801621f commit 37af6d1

2 files changed

Lines changed: 7 additions & 1 deletion

File tree

.github/configs/nvidia-master.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2481,7 +2481,7 @@ kimik2.5-int4-b300-vllm:
24812481
- { tp: 4, ep: 1, conc-start: 4, conc-end: 64 }
24822482

24832483
kimik2.5-int4-h200-vllm:
2484-
image: vllm/vllm-openai:v0.20.2
2484+
image: vllm/vllm-openai:v0.21.0
24852485
model: moonshotai/Kimi-K2.5
24862486
model-prefix: kimik2.5
24872487
runner: h200

perf-changelog.yaml

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2493,3 +2493,9 @@
24932493
- "Update image tag to vllm/vllm-openai:v0.20.2"
24942494
- "Add DEP configs for B300 vLLM MTP"
24952495
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1271
2496+
2497+
- config-keys:
2498+
- kimik2.5-int4-h200-vllm
2499+
description:
2500+
- "Update vLLM image from v0.20.2 to v0.21.0"
2501+
pr-link: XXX

0 commit comments

Comments
 (0)