[AMD][AgentX] kimik2.7: split Mooncake into its own tune key (fail-fast isolation)

The DEP Mooncake c16 cell fails fast at bringup; GH matrix fail-fast then
cancels the still-running LMCache/pure-TP cells before they finish. Split the
LMCache scaling experiment (-tune) from Mooncake (-tune-mc) so a Mooncake
bringup failure can't poison the scaling run, and so Mooncake runs alone and
uploads its own server_logs for diagnosis.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Author: hyukjlee

configs/amd-master.yaml

@@ -574,9 +574,10 @@ kimik2.7-fp4-mi355x-vllm-agentic:
 # Perf-tuning experiment key (same recipe as the record sweep above, via
 # model-prefix kimik2.7). Goal: get a throughput curve that scales with
 # concurrency instead of collapsing. Compares pure-TP8 (current, capacity-capped)
-# vs DEP (data-parallel attention TP1xDP8 + expert parallelism), each with an
-# LMCache/Mooncake KV tier. Dispatched at 900s via e2e-tests duration override to
-# verify the perf delta before committing a full 3600s run.
+# vs DEP (data-parallel attention TP1xDP8 + expert parallelism), both with LMCache.
+# Dispatched at 900s via e2e-tests duration override to verify the perf delta
+# before committing a full 3600s run. Mooncake is split into a separate key
+# (-tune-mc) so a fast Mooncake bringup failure can't fail-fast-cancel these cells.
 kimik2.7-fp4-mi355x-vllm-agentic-tune:
   image: vllm/vllm-openai-rocm:v0.24.0
   model: amd/Kimi-K2.7-Code-MXFP4
@@ -592,7 +593,22 @@ kimik2.7-fp4-mi355x-vllm-agentic-tune:
       search-space:
       - { tp: 8, dp-attn: false, ep: 1, kv-offloading: dram, kv-offload-backend: { name: lmcache, version: "aaf7c0d3" }, conc-list: [16, 32, 48] }
       - { tp: 8, dp-attn: true,  ep: 8, kv-offloading: dram, kv-offload-backend: { name: lmcache, version: "aaf7c0d3" }, conc-list: [16, 32, 48] }
-      - { tp: 8, dp-attn: true,  ep: 8, kv-offloading: dram, kv-offload-backend: { name: mooncake, version: "source-main" }, conc-list: [16, 32, 48] }
+
+# Mooncake-under-DEP, isolated so its failure can't cancel the LMCache scaling run.
+kimik2.7-fp4-mi355x-vllm-agentic-tune-mc:
+  image: vllm/vllm-openai-rocm:v0.24.0
+  model: amd/Kimi-K2.7-Code-MXFP4
+  model-prefix: kimik2.7
+  runner: cluster:mi355x-amds
+  precision: fp4
+  framework: vllm
+  multinode: false
+  scenarios:
+    agentic-coding:
+    - dram-utilization: 0.80
+      duration: 900
+      search-space:
+      - { tp: 8, dp-attn: true, ep: 8, kv-offloading: dram, kv-offload-backend: { name: mooncake, version: "source-main" }, conc-list: [16, 32, 48] }
 
 
 kimik2.5-fp4-mi355x-atom: