diff --git a/perf-changelog.yaml b/perf-changelog.yaml index c250f11f4..4f0e4e4f1 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -4788,3 +4788,10 @@ - "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: + - "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/2222