Metadata-Version: 2.4
Name: llmtrafficlens
Version: 0.6.0
Summary: Profile LLM gateway logs for prefix-cache reuse potential, and export anonymized replayable traces
Project-URL: Homepage, https://github.com/GMISWE/llmtrafficlens
Author: Jason Zhu
License-Expression: Apache-2.0
License-File: LICENSE
Keywords: benchmark,kv-cache,llm,mooncake,prefix-cache,trace,traffic-analysis,workload-characterization
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: System :: Benchmark
Requires-Python: >=3.10
Description-Content-Type: text/markdown

# llmtrafficlens

[![PyPI](https://img.shields.io/pypi/v/llmtrafficlens.svg)](https://pypi.org/project/llmtrafficlens/)
[![Python](https://img.shields.io/pypi/pyversions/llmtrafficlens.svg)](https://pypi.org/project/llmtrafficlens/)
[![License](https://img.shields.io/pypi/l/llmtrafficlens.svg)](LICENSE)

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.

On the public Mooncake conversation trace, which the
[Try it](#try-it-on-a-public-trace) section below reproduces verbatim:

```console
$ llmtrafficlens profile conversation_trace.jsonl --format mooncake -o report
12,031 requests · unknown
input p50 6,909 tok · output p50 350 tok · stream 0% · 3.4 req/s

hit rate by cache size
      16K tokens    3.3%
      64K tokens    4.2%
     256K tokens    4.3%
       1M tokens    5.6%
       4M tokens   18.5%
      16M tokens   34.2%
       unbounded   37.4%  <- ceiling

session identifiers  0.0% of requests  (affinity routing cannot reach this reuse)
top prefix by volume 512 tok x 12,031 reqs = 5.3% of reusable volume
top prefix by count  512 tok x 12,031 reqs = 5.3% of reusable volume

wrote report.json, report.html
```

`report.html` carries the full leaderboards and distributions;
`report.json` is the same content for scripts.

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

```bash
pip install llmtrafficlens
```

No runtime dependencies. Python ≥ 3.10.

## profile

```bash
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.** A summary on stdout (shown above), plus `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

```bash
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:

```json
{"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.

```bash
# 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:

```bash
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
```

That prints the summary at the top of this README. Reading the curve: this
workload gains almost nothing below 1M tokens, and most of its ceiling
needs a cache past 16M — which for GLM-5.2 at bf16 (93 KiB/token) is
1.5 TiB, more than device memory alone holds, and the case tiered KV
stores (host memory, SSD) are built for.

Cache size is reported 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](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
