Skip to content

[Klaud Cold] Revert "Add Kimi K2.6 NVFP4 B300 EAGLE3 AgentX benchmark" (#2158) / 回滚 Kimi K2.6 NVFP4 B300 EAGLE3 AgentX 基准测试（#2158） #2227

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
functionstackx merged 1 commit into from
Jul 15, 2026
Merged

[Klaud Cold] Revert "Add Kimi K2.6 NVFP4 B300 EAGLE3 AgentX benchmark" (#2158) / 回滚 Kimi K2.6 NVFP4 B300 EAGLE3 AgentX 基准测试（#2158） #2227

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
125 changes: 0 additions & 125 deletions benchmarks/single_node/agentic/kimik2.5_fp4_b300_mtp.sh
View file
Open in desktop

This file was deleted.

18 changes: 0 additions & 18 deletions configs/nvidia-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2989,24 +2989,6 @@ kimik2.5-fp4-b300-vllm-agentic:
- { tp: 8, ep: 1, kv-offloading: none, conc-list: [1, 2, 4, 8, 16, 32, 40, 48, 56, 64] }
- { tp: 8, ep: 1, kv-offloading: dram, kv-offload-backend: { name: vllm-simple }, conc-list: [1, 2, 4, 8, 16, 32, 40, 48, 56, 64] }

kimik2.5-fp4-b300-vllm-agentic-mtp:
image: vllm/vllm-openai:nightly-94c0ef300180f8fd1071d9cbe7270a8348155f94
model: Kimi-K2.6-NVFP4
model-prefix: kimik2.5
runner: cluster:b300-nv
precision: fp4
framework: vllm
multinode: false
scenarios:
agentic-coding:
- dram-utilization: 0.80
search-space:
- { tp: 8, ep: 1, spec-decoding: mtp, kv-offloading: none, conc-list: [1] }
- { tp: 4, ep: 1, spec-decoding: mtp, kv-offloading: none, conc-list: [2, 4, 8] }
- { tp: 4, ep: 1, spec-decoding: mtp, kv-offloading: dram, kv-offload-backend: { name: native }, conc-list: [8, 16, 32] }
- { tp: 4, ep: 1, spec-decoding: mtp, dcp-size: 4, kv-offloading: none, conc-list: [32, 64, 80, 96, 112, 128] }
- { tp: 4, ep: 1, spec-decoding: mtp, dcp-size: 4, kv-offloading: dram, kv-offload-backend: { name: native }, conc-list: [64, 80, 96, 112, 128, 144, 160] }

dsr1-fp8-b200-trt:
image: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc14
model: deepseek-ai/DeepSeek-R1-0528
Expand Down
7 changes: 0 additions & 7 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4782,13 +4782,6 @@
- "Clean the export envs"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2198

- config-keys:
- kimik2.5-fp4-b300-vllm-agentic-mtp
description:
- "Add EAGLE3 speculative-decoding arm for the Kimi K2.6 NVFP4 B300 AgentX recipe (draft lightseekorg/kimi-k2.6-eagle3-mla, TOKENSPEED_MLA attention backend with TRT-LLM ragged MLA kernel)."
- "TP8/TP4 GPU-only KV points plus a TP4 native CPU-offload ladder via SimpleCPUOffloadConnector with lazy_offload off; TP4/DCP4 high-concurrency points (conc 32/64) using num_speculative_tokens=3 and synthetic_acceptance_length=2.88."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2158

- config-keys:
- kimik2.5-fp4-b300-vllm-agentic-mtp
description:
Expand Down
1 change: 0 additions & 1 deletion runners/launch_b300-nv.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -352,7 +352,6 @@ else
Kimi-K2.5
Kimi-K2.5-NVFP4
Kimi-K2.6
Kimi-K2.6-NVFP4
MiniMax-M2.5
MiniMax-M2.5-NVFP4
MiniMax-M2.7
Expand Down
2 changes: 1 addition & 1 deletion utils/process_changelog.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -270,7 +270,7 @@ def main():

# Validate final results structure
validated = ChangelogMatrixEntry.model_validate(final_results)
print(validated.model_dump_json(by_alias=True, exclude_none=True))
print(validated.model_dump_json(by_alias=True))


if __name__ == "__main__":
Expand Down