Agentic workload PD separation analysis with trace-driven benchmarks

Systematic study of prefill-decode disaggregation for agentic LLM workloads
using production GLM-5.1 coder trace (2.1M requests, 71B input tokens).

Key findings:
- Cache-aware routing improves TPOT p90 by 15% and APC from 20.8% to 44.7%
  without PD separation, matching PD-Sep's decode isolation benefit
- PD separation adds +72% TTFT overhead (KV transfer) with no TPOT gain
  when using the same cache-aware scheduler
- Prefill remains compute-bound even at 95% KV cache reuse (AI >1000x
  vs decode AI <2), but absolute FLOPs drop 71% from cache hits
- For agentic MoE workloads, cache-aware routing > PD separation

Infrastructure:
- Trace sampler preserving session structure + hash_ids for prefix sharing
- Async trace replayer with streaming TTFT/TPOT/E2E measurement
- Unified cache-aware + token-level load-balanced global scheduler proxy
  supporting both PD-colocated and PD-disaggregated (Mooncake/RDMA) modes
- vLLM 0.18.1 scheduler patch for KV transfer abort race condition
- Roofline analysis tool for prefill/decode compute characterization

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

pyproject.toml

@@ -0,0 +1,16 @@
+[project]
+name = "agentic-kv"
+version = "0.1.0"
+description = "Trace-driven KV cache benchmarking for agentic LLM workloads"
+requires-python = ">=3.10"
+dependencies = [
+    "httpx>=0.27",
+    "numpy>=1.24",
+]
+
+[project.optional-dependencies]
+dev = ["pytest"]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"