We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent c07bf5d commit 16717b6Copy full SHA for 16717b6
2 files changed
.github/configs/nvidia-master.yaml
@@ -2684,7 +2684,7 @@ kimik2.5-fp4-b200-vllm-agentic:
2684
# Kimi-K2.5 FP4 B200 vLLM recipe as-is until B300-specific tuning is available.
2685
2686
kimik2.5-fp4-b300-vllm:
2687
- image: vllm/vllm-openai:v0.19.0-cu130
+ image: vllm/vllm-openai:v0.21.0
2688
model: nvidia/Kimi-K2.5-NVFP4
2689
model-prefix: kimik2.5
2690
runner: b300
perf-changelog.yaml
@@ -2629,3 +2629,9 @@
2629
description:
2630
- "Update vLLM ROCm image from v0.18.0 to v0.21.0"
2631
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