Skip to content

Commit 16717b6

Browse files
Update kimik2.5-fp4-b300-vllm vLLM image to v0.21.0
1 parent c07bf5d commit 16717b6

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
@@ -2684,7 +2684,7 @@ kimik2.5-fp4-b200-vllm-agentic:
26842684
# Kimi-K2.5 FP4 B200 vLLM recipe as-is until B300-specific tuning is available.
26852685

26862686
kimik2.5-fp4-b300-vllm:
2687-
image: vllm/vllm-openai:v0.19.0-cu130
2687+
image: vllm/vllm-openai:v0.21.0
26882688
model: nvidia/Kimi-K2.5-NVFP4
26892689
model-prefix: kimik2.5
26902690
runner: b300

perf-changelog.yaml

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2629,3 +2629,9 @@
26292629
description:
26302630
- "Update vLLM ROCm image from v0.18.0 to v0.21.0"
26312631
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1404
2632+
2633+
- config-keys:
2634+
- kimik2.5-fp4-b300-vllm
2635+
description:
2636+
- "Update vLLM image from v0.19.0-cu130 (27d old) to v0.21.0"
2637+
pr-link: PLACEHOLDER

0 commit comments

Comments
 (0)