diff --git a/benchmarks/single_node/agentic/kimik3_fp4_mi355x_mtp.sh b/benchmarks/single_node/agentic/kimik3_fp4_mi355x_mtp.sh index f0416e4af0..f43c6ed13a 100644 --- a/benchmarks/single_node/agentic/kimik3_fp4_mi355x_mtp.sh +++ b/benchmarks/single_node/agentic/kimik3_fp4_mi355x_mtp.sh @@ -149,7 +149,7 @@ case "${KV_OFFLOAD_BACKEND:-}" in lmcache) require_agentic_kv_offload_backend "$KV_OFFLOAD_BACKEND" - LMCACHE_VERSION=0.5.5.dev89+rocm7.2 + LMCACHE_VERSION=0.5.5.dev114+rocm7.2 LMCACHE_ROCM_INDEX="https://github.com/LMCache/LMCache/releases/expanded_assets/nightly-rocm" agentic_pip_install --quiet --no-cache-dir --no-deps \ diff --git a/configs/amd-master.yaml b/configs/amd-master.yaml index 18007db0dd..8f6d246d2e 100644 --- a/configs/amd-master.yaml +++ b/configs/amd-master.yaml @@ -637,8 +637,8 @@ kimik3-fp4-mi355x-vllm-agentic-mtp: - dram-utilization: 0.60 search-space: - { tp: 8, ep: 1, dcp-size: 1, kv-offloading: none, conc-list: [1] , spec-decoding: mtp} - - { tp: 8, ep: 1, dcp-size: 1, kv-offloading: dram, kv-offload-backend: { name: lmcache, version: "0.5.5.dev89+rocm7.2" }, conc-list: [4, 8, 10, 12, 14], spec-decoding: mtp } - - { tp: 8, ep: 1, dcp-size: 8, kv-offloading: dram, kv-offload-backend: { name: lmcache, version: "0.5.5.dev89+rocm7.2" }, conc-list: [44, 48, 52], spec-decoding: mtp } + - { tp: 8, ep: 1, dcp-size: 1, kv-offloading: dram, kv-offload-backend: { name: lmcache, version: "0.5.5.dev114+rocm7.2" }, conc-list: [4, 8, 10, 12, 14], spec-decoding: mtp } + - { tp: 8, ep: 1, dcp-size: 8, kv-offloading: dram, kv-offload-backend: { name: lmcache, version: "0.5.5.dev114+rocm7.2" }, conc-list: [44, 48], spec-decoding: mtp } # Kimi-K3 MXFP4 agentic-coding benchmark on MI355X via ATOM with DSpark # speculative decoding. Acceptance is pinned to the committed golden curve in diff --git a/perf-changelog.yaml b/perf-changelog.yaml index b05aba27c6..e9fab1e0d8 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -6970,6 +6970,15 @@ - "Resolve draft-model jobs through the existing B200 SGLang speculative recipe and the staged DeepSeek-V4-Pro-0813 checkpoint." pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2821 +- config-keys: + - kimik3-fp4-mi355x-vllm-agentic-mtp + scenario-type: + - agentic-coding + description: + - "Upgrade the Kimi-K3 MI355X vLLM AgentX LMCache build from 0.5.5.dev89+rocm7.2 to 0.5.5.dev114+rocm7.2 from the nightly ROCm release index; the rolling release no longer publishes the intermediate 0.5.5.dev104+rocm7.2 wheel." + - "Preserve the image, runtime settings, and topology from the full sweep in Actions run 33773561410; run concurrency 1 without offload and LMCache concurrencies 4, 8, 10, 12, 14, 44, and 48, with 48 as the upper bound." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2889 + - config-keys: - dsv4-fp4-mi355x-vllm - dsv4-fp4-mi355x-vllm-mtp