llmtrafficlens 0.5.0

Profile LLM gateway logs for prefix-cache reuse potential, and export anonymized replayable traces

llmtrafficlens

Analyze an LLM gateway's request log for prefix-cache reuse, then export the log as an anonymized trace that standard benchmark tools can replay.

Two commands:

• profile — how much a prefix cache could save on this traffic, and how much cache memory that takes.
• export — the same log as a Mooncake- or bailian-format trace, with all text removed.

Background

An engine serves a request in two phases: prefill reads the whole prompt at once, then decode emits output tokens one by one. Prefill cost grows with prompt length, and it is pure recomputation whenever two requests begin with the same text — the same system prompt, the same few-shot examples, the same attached document.

A prefix cache avoids that: the intermediate state a prompt produces (its KV cache) stays in memory, and the next request starting with the same text reuses it instead of recomputing. Whether that pays off depends on three things, which are exactly what this tool reports:

• The traffic. If requests share no leading text, nothing can be reused. This is a property of your workload, not of your setup.
• Cache memory. KV state is bulky, so a cache holds a bounded number of tokens and evicts the rest. More memory, more hits — with diminishing returns you can measure instead of guess.
• Routing. Across several workers, a request only hits if it reaches the worker that already holds its prefix. Sending it there is what prefix-aware routing does; the alternative, session affinity, only works when requests carry a session identifier.

Reuse is tracked in fixed-size blocks (16 tokens by default) because engines cache at block granularity, not per character.

Install

pip install llmtrafficlens

No runtime dependencies. Python ≥ 3.10.

profile

llmtrafficlens profile gateway.csv -o report

Input. A CSV with a request_json column holding the OpenAI-format request body. These columns are used when present: response_json, model_name, status_code, and a timestamp column (timestamp, ts, created_at, ...; epoch or ISO-8601, or set --ts-column). Mooncake and qwen-bailian traces are accepted as input too (--format mooncake|bailian).

Output. report.html and report.json, containing:

• hit rate at each cache size, ending with the unbounded case — the ceiling;
• top prefixes by reuse count, and separately by reusable token volume;
• share of requests carrying a session identifier;
• input/output token distributions, streaming ratio, model mix, QPS.

How to read it.

Ceiling — the share of input tokens that could be served from cache if memory were unlimited and every request reached the right worker. It bounds everything else: at a few percent, no amount of engineering makes prefix caching worthwhile on this traffic.

Capacity curve — the hit rate at each cache size, so you can see what the ceiling costs. Where it flattens is the point past which buying memory stops helping.

Session-identifier share — whether the cheap option is enough. When most requests carry an identifier, pinning each session to a worker captures the reuse. When none do (a common case for API traffic), the reuse sits in prefixes shared between unrelated requests, and only prefix-aware routing reaches it.

The two leaderboards — which prefixes to keep resident. They rank differently, and the token-volume one is what determines savings: a short prefix reused very often contributes almost no reusable volume, while a long prefix reused a few dozen times can account for most of it.

export

llmtrafficlens export gateway.csv --to mooncake -o trace.jsonl   # or --to bailian

A benchmark written by hand, with equally popular prompt groups, reports a higher hit rate than production reaches, because every group stays warm. Replaying the real log avoids that, and the export can be shared, because each request is reduced to one line of structure:

{"timestamp": 1753340000123, "input_length": 1994, "output_length": 117,
 "hash_ids": [4251731047194047120, 8125214104179782736, ...]}

hash_ids is a salted chained block hash: two requests share their first N hashes exactly when they share their first N blocks. Replay tools generate one synthetic block per hash, so the prefix-sharing structure is preserved while the content is not real.

# replay at the recorded pace
aiperf profile --custom-dataset-type mooncake_trace --input-file trace.jsonl --fixed-schedule ...
# replay at 2x the pace, for rate sweeps
aiperf profile --custom-dataset-type mooncake_trace --input-file trace.jsonl --synthesis-speedup-ratio 2.0 ...
# or SGLang
python -m sglang.bench_serving --dataset-name mooncake --dataset-path trace.jsonl ...

--to bailian adds chat_id, parent_chat_id and turn for AIPerf's bailian_trace mode; use it when the log carries session identifiers. Tell the consumer which block size the export used — AIPerf defaults to 512 for mooncake and 16 for bailian (--prompt-input-tokens-block-size).

Try it on a public trace

No data of your own needed:

curl -LO https://raw.githubusercontent.com/kvcache-ai/Mooncake/main/FAST25-release/traces/conversation_trace.jsonl
llmtrafficlens profile conversation_trace.jsonl --format mooncake -o mooncake-report

The curve over those 12,031 requests, with cache size priced as GLM-5.2 KV at bf16:

cache size	as GLM-5.2 KV	hit rate
16K tokens	1.5 GiB	3.3%
64K	5.8 GiB	4.2%
256K	23 GiB	4.3%
1M	93 GiB	5.6%
4M	372 GiB	18.5%
16M	1.5 TiB	34.2%
unbounded	—	37.4% (ceiling)

This workload gains almost nothing below 1M tokens, and most of its ceiling needs KV storage past a terabyte — more than device memory alone holds, which is the case tiered KV stores (host memory, SSD) are built for.

Cache size is in tokens because bytes are model-specific: 93 KiB/token for GLM-5.2, 68.6 for Kimi K2.5, 128 for a 32-layer fp16 GQA model. Some architectures also carry a DSA indexer cost on top of attention. Look yours up with kvcache-simulator list-models.

The repository also contains a synthetic sample log (examples/, not shipped in the pip package): 360 requests, three shared system prompts with skewed popularity, sparse session identifiers, real timestamps. It reports a 66.4% ceiling, and it shows the two leaderboards disagreeing — 16 tokens × 180 requests is 2.3% of the reusable volume, while 2400 tokens × 30 requests is 55.6% of it.

Methodology and validation

Metric definitions and their sources, the per-model KV byte accounting, and what has been checked are in METHODOLOGY.md. In short: our block matching reproduces NVIDIA AIPerf's analyze-trace to 5e-15 on the same trace, and the official kvcache-simulator's ceiling once its warm-up window is applied. Not yet verified: an export actually replaying through AIPerf or SGLang.

Privacy

Processing is local. Reports contain aggregates only. An export contains lengths, timestamps, anonymized session identifiers and salted block hashes; prompts cannot be reconstructed from it. The hash key is written to .ltl-salt on first run — keep it unchanged so runs stay comparable, and treat it as a secret.

Scope

We do not replay traffic, control request rate, or search deployment configurations. AIPerf, SGLang bench_serving and simulators such as Vidur do that, and all of them take a trace as input. Observability platforms record token counts and cost per request, not prefix structure; trace analyzers require an already-hashed trace. This tool covers the step between: raw gateway log to hashed trace.

License

Apache-2.0