Skip to content

[chore] bump kimi-k2.5 int4 b200/b300 vllm images to v0.25.0 / [chore] 将 kimi-k2.5 int4 b200/b300 vLLM 镜像升级至 v0.25.0 #2256

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
adibarra merged 3 commits into from
Jul 18, 2026
+9 −6
Merged

[chore] bump kimi-k2.5 int4 b200/b300 vllm images to v0.25.0 / [chore] 将 kimi-k2.5 int4 b200/b300 vLLM 镜像升级至 v0.25.0 #2256

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
6c94e1d
bump kimi-k2.5 int4 b200/b300 vllm images to v0.25.0
xinli-sw Jul 17, 2026
15e02e9
bump kimi-k2.5 int4 b200/b300 vllm images to v0.25.0
xinli-sw Jul 17, 2026
62a18cd
bump kimi-k2.5 int4 b200/b300 vllm images to v0.25.0
xinli-sw Jul 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 2 additions & 6 deletions configs/nvidia-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1969,7 +1969,7 @@ qwen3.5-bf16-b300-sglang-mtp:
- { tp: 4, ep: 1, conc-start: 4, conc-end: 64, spec-decoding: mtp }

kimik2.5-int4-b200-vllm:
image: vllm/vllm-openai:v0.24.0
image: vllm/vllm-openai:v0.25.0
model: moonshotai/Kimi-K2.5
model-prefix: kimik2.5
runner: b200
Expand All @@ -1983,10 +1983,6 @@ kimik2.5-int4-b200-vllm:
search-space:
- { tp: 8, conc-start: 4, conc-end: 64 }

# NOTE: At the time of submission, https://docs.vllm.ai/projects/recipes/en/latest/moonshotai/Kimi-K2.5.html
# does not have a B300-specific recipe, so this config reuses the existing
# Kimi-K2.5 INT4 B200 vLLM recipe as-is until B300-specific tuning is available.

kimik2.5-int4-b200-vllm-agentic:
image: vllm/vllm-openai:v0.22.0
model: moonshotai/Kimi-K2.5
Expand All @@ -2003,7 +1999,7 @@ kimik2.5-int4-b200-vllm-agentic:
- { tp: 8, kv-offloading: dram, kv-offload-backend: { name: vllm-simple }, conc-list: [32, 64, 96, 128] }

kimik2.5-int4-b300-vllm:
image: vllm/vllm-openai:v0.24.0
image: vllm/vllm-openai:v0.25.0
model: moonshotai/Kimi-K2.5
model-prefix: kimik2.5
runner: b300
Expand Down
7 changes: 7 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4933,3 +4933,10 @@
description:
- "Add MiniMax M3 NVFP4 B300 Dynamo-vLLM disaggregated EAGLE3 recipes"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2182

- config-keys:
- kimik2.5-int4-b200-vllm
- kimik2.5-int4-b300-vllm
description:
- "Bump vLLM image to v0.25.0"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2256