Skills DirectorySearch all skills ↗AI agent skill · by @BBuf
Llm Serving Auto Benchmark
Framework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, TokenSpeed, or another serving framework. Use when a user wants to find the best deployment command for one model across multiple serving frameworks under the same workload, GPU budget, and latency SLA.
Archived 2026-10-23 · Source updated 2026-10-05. Check the original repository for the latest version.
SKILL.md instructions
# LLM Serving Auto Benchmark
## Overview
Use this skill to compare LLM serving frameworks such as SGLang, vLLM,
TensorRT-LLM, and TokenSpeed for the same model and workload.
Use a config-driven workflow:
- keep launch-only capacity choices in each framework's `base_server_flags`
- put the search knobs in `search_space`
- run the same dataset scenarios for every framework
- generate a bounded candidate list from `search_space`, with the baseline
candidate included first
- keep failed candidates in the result file
- pick the best SLA-passing candidate after normalizing the results
For model-specific starting points, prefer the shipped configs in
`configs/cookbook-llm/`. They define a framework-neutral LLM serving cookbook
model set and translate each entry into framework-native SGLang, vLLM, and
TensorRT-LLM, and TokenSpeed server flags. Validate those configs before a real
run:
```bash
python skills/llm-serving-auto-benchmark/scripts/validate_cookbook_configs.py \
skills/llm-serving-auto-benchmark/configs/cookbook-llm/*.yaml
```
If you have captured target-environment `--help` files, add
`--help-dir <artifact-help-dir>`. That check only loads configs, verifies the
server flag names, and renders candidate commands; it does not launch model
servers.
Prefer native tooling when it gives better coverage:
- SGLang: current public cookbooks use `sglang serve`; `python -m
sglang.launch_server` remains accepted. Prefer `python -m sglang.benchmark.serving`
- vLLM: `vllm bench sweep serve` for server-parameter sweeps, otherwise
`vllm serve` plus `vllm bench serve`
- TensorRT-LLM: `trtllm-serve` for the OpenAI-compatible server plus the
TensorRT-LLM serving benchmark client or a common OpenAI-compatible benchmark
client
- TokenSpeed: `tokenspeed serve` for the OpenAI-compatible server plus
`vllm bench serve --backend openai-chat` or the same OpenAI-compatible benchmark client used
for the other frameworks
TensorRT-LLM has one hard scope rule in this skill: the current server is PyTorch-only; older images must select pytorch. Do not search TensorRT-LLM backend
choice. If a request, config, or candidate asks for `trt`, an engine backend, or
any other non-PyTorch TensorRT-LLM server backend, reject that candidate as
unsupported for this skill and record the reason. This does not change the
benchmark client backend; the TensorRT-LLM benchmark client still uses
OpenAI-compatible modes such as `--backend openai` or `--backend openai-chat`.
Only pick a winner after each requested framework has had its main serving knobs
tuned.
Framework selection is caller-controlled. If the caller explicitly supplies a
framework list, benchmark only those enabled frameworks. Do not silently add
TensorRT-LLM or TokenSpeed just because cookbook configs or history docs exist;
record omitted frameworks as user-excluded, not unsupported.
The parameter lists in this skill are not a compatibility contract. They are
version-sensitive candidate knob families. Before every real run, record the
exact framework version or git commit and verify the concrete CLI flag names
with `--help` in the target environment.
The default search style is framework-neutral: start from a mostly pure-TP
baseline, sweep a small set of high-impact runtime knobs, and cap the first
pass around 10 candidates per framework. Do not search memory fractions by
default.
## Source and experiment contracts
Use the [2026-09-18 source contracts](../../docs/upstream-source-contracts.md)
for current profiler APIs, branch-specific defaults and KV sizing semantics.
Before combining PRs or claiming kernel performance/accuracy equivalence, use
[paired-validation.md](references/paired-validation.md). It distinguishes
code-only A/B from deployment tuning, real from simulated acceptance, and
interactivity from aggregate output throughput. Profile after timing to prove
that the candidate backend actually ran.
## Validation Environment
This skill is target-agnostic. It assumes any one of the following is
available, and nothing more:
- a local GPU host with Docker/Podman and the target framework images pulled;
- a remote GPU host reached via `ssh <host>` with the framework images already
running in a container there;
- a CI runner that can exec into a pre-built image for each framework.
Do not assume a specific operator host name inside this skill's own workflow.
The concrete SSH wiring, container names, workspace paths, and HF token plumbing
for a given box live in operator-side per-host skills; this skill only requires
that the caller can reach a shell inside a container with the requested
framework installed.
Reference files are optional and version-sensitive. Treat historical flag notes
as evidence from one image, not as a compatibility guarantee for the next run.
Historical smoke validation on 2026-05-01 (H100) and 2026-06-27 (B200) exercised
small serving/search workloads. The B200 image provided only SGLang; missing
vLLM/TRT-LLM/TokenSpeed CLIs were environment gaps. Those runs are not current
cross-framework speed or accuracy results. The September source refresh ran
offline tooling, not a new GPU matrix.
## Skill Scope
This skill is a playbook plus a config+validator toolchain, not a turn-key
orchestrator. The operator still launches servers, drives workloads, and writes
one normalized JSONL row per candidate.
The `scripts/` directory contains exactly two tools:
- `validate_cookbook_configs.py`: load cookbook YAML, render bounded candidate
server commands, and check flag names against captured `--help` snapshots
without launching servers.
- `compare_benchmark_results.py`: turn normalized per-candidate JSONL into the
markdown and optional CSV tables described in the Output Contract.
Cookbook configs under `configs/cookbook-llm/` must pass the validator. The
shorter [references/example-plan.yaml](references/example-plan.yaml) is a
one-off runtime-plan skeleton and is not expected to pass as-is. Use
[references/result-schema.md](references/result-schema.md) as the single source
of truth for SLA key names.
## Required Inputs
Collect these before a long run:
- model and tokenizer path, target frameworks, GPU model/count, multi-node
allowance, precision, and quantization constraints
- endpoint shape, workload source, dataset scenarios, SLA target, search budget,
and artifact output directory
- version manifest: framework package version or git commit, container/Python
environment, `--help` snapshots, and whether each search parameter was
accepted by that exact CLI
If real production traffic is the goal, use the real request distribution. A
synthetic workload is fine for bring-up and first-pass comparison, but it is not
enough for a production choice.
Record each scenario's input/output length distribution in the normalized
result rows. This is part of the profiler handoff contract: when a framework
is slower and the follow-up investigation invokes `llm-torch-profiler-analysis`,
the profiler workload must reuse the slow benchmark scenario lengths instead of
falling back to its generic prefill `4090->1` and decode `1->2048` defaults.
## Version-sensitive deployment checks
- Consult the [source contracts](../../docs/upstream-source-contracts.md) for
exact inspected revisions. Preserve installed-image `--help` and effective
environment values; do not copy a historical release's defaults forward.
- SGLang main and dsv4.1 differ on FlashInfer fused finalize at the inspected
heads. A numerical default change is part of the experiment, not noise.
The current kernel roots are `python/sglang/kernels/{aot,jit,ops}`.
- SGLang's native `/generate` and OpenAI-compatible paths are different
benchmark lanes. Use one common endpoint/client when comparing frameworks;
separately label any native-client result.
- Match attention/GEMM backend support to the GPU architecture and dtype.
“Blackwell” includes different SM targets; B200/GB300/RTX 5090 are not one
interchangeable backend contract. Verify support in the installed code.
- vLLM DBO depends on a supported all-to-all backend. Compile fusion depends
on platform, graph partition and dtype guards. Confirm dispatch using the
[fusion reference](../llm-torch-profiler-analysis/references/vllm-torch-compile-fusions.md).
- The current TensorRT-LLM lane uses `trtllm-serve serve <model>`; older images may need `--backend pytorch`.
Server backend is distinct from OpenAI benchmark-client backend. Verify the
model format, KV-memory flag spelling and random-dataset sampling options
from the selected CLI; do not silently fall back to another dataset.
- TokenSpeed uses `tokenspeed serve <model>` and a common OpenAI-compatible client.
Its TP/attention-TP/MoE-TP/EP and memory flags need their own interpretation;
similarly named SGLang/vLLM options are not an equivalence guarantee.
- Every max-context candidate must cover `max(input_len + output_len)` across
all scenarios, not just the baseline. The cookbook validator checks this.
- Profile after timing. For a fixed simulated-acceptance curve, label it as
such; restart in real acceptance mode for model accuracy tests. Never promote
an unused replacement kernel because end-to-end scores happen to match.
## Secrets Hygiene
- Never print `HF_TOKEN`, `HUGGINGFACE_HUB_TOKEN`, or any upstream API key into
a saved artifact. Pass them through container `-e VAR` (unquoted on the right
side so the host value is inherited) and keep them out of `server_command`
and `benchmark_command` fields written to the result JSONL.
- When a framework echoes the full argv at startup, scrub the log or redact
token-shaped substrings before uploading the artifact.
## Fairness Rules
Use these rules throughout the benchmark:
- Run every framework on the same GPU type, GPU count, model weights, tokenizer,
precision, quantization policy, prompt distribution, output length target, and
sampling settings.
- Record framework version, git commit, container image, CUDA/NCCL versions, GPU
driver, visible GPU ids, launch command, and benchmark command.
- Warm the server before measuring. Restart or clear state between candidate
configurations when cache effects would bias the comparison.
- Compare steady-state fixed-QPS runs separately from burst throughput runs.
- Keep failed candidates in the final results with their failure reason.
- Report both raw throughput and SLA-passing throughput. The fastest failing
candidate is not the best deployment command.
## Workflow
### 1. Preflight
Verify SGLang plus all requested comparison frameworks before starting a search.
Run only the commands for the requested framework set:
```bash
sglang serve --help
python -m sglang.launch_server --help
python -m sglang.benchmark.serving --help
vllm serve --help
vllm serve --help=all
vllm bench serve --help
vllm bench serve --help=all
vllm bench sweep serve --help=all
trtllm-serve serve --help
python -m tensorrt_llm.serve.scripts.benchmark_serving --help
tokenspeed serve --help
vllm bench serve --help
```
Use the framework-specific `--help` output in the target environment as the
source of truth. Do not keep a stale launch flag just because it appears in an
old note.
vLLM 0.19 and newer use grouped help. Plain `vllm serve --help` only shows the
groups, so capture `--help=all` before deciding whether a search knob exists.
Save these `--help` outputs into the run artifact directory. If a listed search
knob is missing from the current CLI, remove or translate that knob before
running the benchmark. Do not silently pass unknown flags.
Record `trtllm-serve serve --help`. Current main is PyTorch-only; omit its
deprecated backend option. On older images listing multiple backends, select
`--backend pytorch`.
For TokenSpeed, confirm both the server and benchmark entrypoints because some
installations alias the binary as `ts`. Record the exact binary used in
`server_command`.
For each framework, launch a minimal server, confirm `/v1/models` or the native
model-info endpoint, send one streaming request, run one tiny benchmark with at
least 5 requests, then save the launch command, benchmark command, server log,
and benchmark output.
Before any GPU-backed smoke run, check the requested GPU ids directly with
`nvidia-smi`. If a requested GPU is already in use, stop and record that fact.
Do not silently borrow a different GPU count for a performance comparison. It is
fine to run a smaller one-GPU smoke only when the result is clearly labeled as a
flow check rather than a fair throughput comparison.
If the target environment runs through containers, follow
[references/container-runbook.md](references/container-runbook.md) and save image
tags, pull commands, launch/benchmark logs, and cleanup commands.
### 2. Normalize The Workload
Use one canonical workload for all frameworks. Recommended JSONL row shape:
```json
{"prompt": [{"role": "user", "content": "Summarize this text."}], "output_len": 256}
{"prompt": "Write a short explanation of CUDA graphs.", "output_len": 128}
```
Optional fields:
```json
{
"prompt": [{"role": "user", "content": "Use low temperature."}],
"output_len": 256,
"extra_request_body": {"temperature": 0.0, "top_p": 0.95},
"metadata": {"source": "prod-sample"}
}
```
When converting user data:
- inspect at least 3 rows before conversion
- preserve request-level sampling options in `extra_request_body`
- do not include the final assistant answer in the prompt when that answer is
the target completion
- keep multimodal or tool-call payloads only if all requested frameworks support
the chosen endpoint shape
For synthetic bring-up, use the shipped two-scenario shape:
```yaml
dataset:
kind: random
num_prompts: 80
scenario_names: [chat, summarization]
input_len: [1000, 8000]
output_len: [1000, 1000]
```
Each aligned `input_len` / `output_len` pair is one scenario. Do not take the
cartesian product unless the user asks for that.
Name each scenario and keep the aligned pair in the artifacts. For custom
datasets, compute or record representative `input_len` and `output_len`
buckets, at least p50 and p95 when possible, so later profiler runs can match
the slow bucket rather than profiling an unrelated synthetic shape.
Before searching any sequence-length limit, compute the largest
`input_len + output_len` in the dataset. SGLang `context_length`, vLLM
`max_model_len`, TensorRT-LLM `max_seq_len`, and TokenSpeed `max_model_len`
must be at least that value for every candidate that is expected to run all
scenarios.
### 3. Pick A Search Tier
Use the smallest tier that can answer the user's question:
- Tier 1: smoke and sanity. One baseline plus a few high-impact knobs.
- Tier 2: default. A bounded sweep over the most likely server settings.
- Tier 3: exhaustive. Only when the search space is already tight and the user
accepts a long run.
Default budget:
- `num_prompts: 80` for the default cross-framework comparison; `num_prompts:
20` per scenario is acceptable for a smoke/flow check and must be labeled as
such in the artifact (not as a performance result).
- `search.max_candidates_per_framework: 10` for the first useful pass
- candidate generation: baseline first, then a bounded product or ordered
candidate list from `search_space`
- at most 5 QPS search rounds unless the user asks for more
- stop early when every candidate in one framework is clearly OOM or fails the
basic health check
Keep these in `base_server_flags` unless the user specifically wants a capacity
or memory study:
- SGLang `mem_fraction_static`
- SGLang `schedule_policy`
- vLLM `gpu_memory_utilization`
- TensorRT-LLM `kv_cache_free_gpu_memory_fraction`
- TokenSpeed `gpu_memory_utilization`
These are real knobs, but they widen the search quickly and often turn a serving
comparison into a memory-limit study.
### 4. Tune SGLang
Launch each SGLang candidate manually. The auto-benchmark module was removed in #31941.
Benchmark with the current serving client:
```bash
python -m sglang.benchmark.serving \
--backend sglang \
--dataset-name random \
--random-input-len 1024 \
--random-output-len 256 \
--num-prompts 80 \
--request-rate 8 \
--output-file /path/to/sglang/results.json \
--output-details
```
Version-sensitive SGLang knob families to verify:
- `tp_size`, `pp_size`, `dp_size` (replicas), `attn_dp_size`, `ep_size`
- `attention_backend`, `prefill_attention_backend`, `decode_attention_backend`
- `sampling_backend`
- `max_running_requests`, `max_queued_requests`
- `chunked_prefill_size`, `prefill_max_requests`, `max_prefill_tokens`
- `max_total_tokens`, `page_size`
- phase-specific CUDA graph settings
- speculative or EAGLE settings only after the non-speculative baseline is tuned
Keep `mem_fraction_static` and `schedule_policy` pinned in the default pass,
matching the shared cookbook config style.
For quick smoke tests, use `--cuda-graph-backend-decode disabled` and
`--cuda-graph-backend-prefill disabled` if the goal is only to prove the framework flow. Record those
flags in the artifact. Do not carry that smoke setting into a performance winner
unless the user asked to tune eager-mode serving.
### 5. Tune vLLM
Use vLLM's sweep runner when available:
```bash
vllm bench sweep serve \
--serve-cmd 'vllm serve <model> --port 8000' \
--bench-cmd 'vllm bench serve --backend vllm --model <model> --port 8000 --dataset-name random --num-prompts 80' \
--serve-params /path/to/vllm_serve_params.json \
--bench-params /path/to/vllm_bench_params.json \
--output-dir /path/to/vllm_results
```
If sweep support is unavailable, run `vllm serve` for each candidate and measure
with `vllm bench serve`.
Version-sensitive vLLM knob families to verify:
- tensor, pipeline, data, decode-context, and expert parallelism
- `gpu_memory_utilization`
- `max_num_seqs`
- `max_num_batched_tokens`
- `max_model_len`
- `enable_chunked_prefill`, `long_prefill_token_threshold`, and DBO thresholds
- KV cache dtype and block size
- dtype and quantization settings
- CUDA graph capture sizes or eager-mode toggles when relevant
- prefix cache and speculative decoding settings only when the workload needs
those features
vLLM should get a normal sweep, not one baseline command. See
[references/framework-reference.md](references/framework-reference.md) for
native command templates and cross-framework knob families. Confirm each flag on
the target image's `--help` before a run.
Keep `gpu_memory_utilization` in the baseline for the default pass. Search it
only when the question is explicitly about fitting the model or trading capacity
against throughput.
Keep DBO and all2all backend settings out of the default pass unless the target
vLLM environment is already set up for them. They are real tuning knobs, but a
candidate can fail at startup if the required all2all backend is not available.
Verify `long_prefill_token_threshold` on the concrete `vllm serve --help=all`
surface before adding it to a search.
### 6. Tune TensorRT-LLM
Use `trtllm-serve serve` as the server entrypoint when the target environment
supports it:
```bash
trtllm-serve serve <model> \
--tp_size <tp> \
--pp_size <pp> \
--kv_cache_free_gpu_memory_fraction 0.75 \
--host 0.0.0.0 \
--port 8000
```
Then benchmark the OpenAI-compatible endpoint with the TensorRT-LLM serving
benchmark client or with the same OpenAI-compatible client used for the other
frameworks.
In the historical TensorRT-LLM 1.0.0 validation image,
`benchmark_serving --dataset-name random` sampled from ShareGPT unless either
`--download-path` or `--random-ids` was passed. For a fast synthetic smoke test,
pass `--random-ids`, then confirm the behavior on the target TensorRT-LLM image.
TensorRT-LLM flag names are especially version-sensitive. Historically, in the validated
TensorRT-LLM 1.0.0 image, the KV-cache memory flag accepted by
`trtllm-serve serve` was `--kv_cache_free_gpu_memory_fraction`, not
`--free_gpu_memory_fraction`. Current mainline was rechecked at
`bb367fc8c1adf6e2c28c88cb1a8b46e1742a9d60` on 2026-10-05. Always verify flags
with `trtllm-serve serve --help` before running a search on any GPU target.
TensorRT-LLM backend policy for this skill:
- launch the PyTorch-only current server without its deprecated backend option
- use `backend: pytorch` only as an older-image compatibility setting
- do not add `backend` to `search_space`
- reject `trt`, engine-backed serving, or any other non-PyTorch TensorRT-LLM
server backend as unsupported for this skill
Version-sensitive TensorRT-LLM knob families to verify:
- `tp_size`, `pp_size`, and `ep_size`
- max batch size, max sequence length, max number of tokens, and KV-cache budget
- inflight batching and scheduler options
- extra LLM API options YAML used by `trtllm-serve` with the PyTorch backend
The `trtllm-serve serve` CLI exposes fewer direct runtime knobs than SGLang or
vLLM. Use direct flags when they exist, then use `--extra_llm_api_options` for
PyTorch-backend settings that are not top-level CLI flags. Keep unsupported
backend or engine requests in the failure table instead of translating them.
Keep `kv_cache_free_gpu_memory_fraction` in the baseline for the default pass.
Search `max_batch_size`, `max_num_tokens`, `max_seq_len`, and validated
PyTorch-backend config options first. The server backend remains fixed to
`pytorch`.
### 7. Tune TokenSpeed
Use TokenSpeed as a first-class comparison framework, especially for agentic or
multi-turn workloads where it may be the strongest non-SGLang baseline:
```bash
tokenspeed serve <model> \
--host 0.0.0.0 \
--port 8000 \
--tensor-parallel-size <tp> \
--gpu-memory-utilization 0.90 \
--max-model-len 12288 \
--max-num-seqs 64 \
--chunked-prefill-size 8192 \
--kv-cache-dtype auto \
--trust-remote-code
```
Benchmark either with the common OpenAI-compatible benchmark client:
```bash
vllm bench serve --backend openai-chat \
--base-url http://127.0.0.1:8000 \
--model <model> \
--dataset-name random \
--random-input-len 1024 \
--random-output-len 256 \
--num-prompts 80
```
or with the same OpenAI-compatible client used for the other frameworks.
When TokenSpeed is a likely leader and profiler handoff will be needed, the
control server can arm torch profiling for the same request shape (CONTROL_PORT defaults to the serving port + 1; override with --control-port):
```bash
curl -X POST "http://127.0.0.1:${CONTROL_PORT}/start_profile" \
-H 'Content-Type: application/json' \
-d '{"output_dir":"/artifacts/tokenspeed_profile","num_steps":5,"activities":["CPU","GPU"],"with_stack":true,"profile_id":"ts-bench"}'
# Drive the same workload with the common client, then POST /stop_profile if needed.
```
If `output_dir` is not supplied, TokenSpeed writes under
`TOKENSPEED_PROFILER_DIR`, defaulting to `/tmp`.
For large MoE or agentic checkpoints, validate these TokenSpeed knobs before
adding them to the search:
- `tensor_parallel_size`, `attn_tp_size`, `moe_tp_size`, and
`enable_expert_parallel`
- `attention_backend`, `drafter_attention_backend`, `moe_backend`, and
`draft_moe_backend`
- `max_num_seqs`, `chunked_prefill_size`, `max_prefill_tokens`, and
`max_total_tokens`
- `kv_cache_dtype`, `quantization`, and prefix-cache controls
- speculative flags such as `speculative_algorithm`, `speculative_num_steps`,
and `speculative_num_draft_tokens`
- `comm_fusion_max_num_tokens`, `enable_allreduce_fusion`, and related
communication-fusion flags only after a target-image smoke run
If a TokenSpeed-native agentic config exists for the same model family, run it
as an additional workload lane rather than replacing the common cross-framework
scenario. Normalize its result rows with the same schema and mark
`workload.kind` accordingly.
Keep `gpu_memory_utilization` pinned in the default pass. Search it only when
the user explicitly wants a capacity study.
### 8. Normalize Results
Write one JSONL row per candidate using the schema in
[references/result-schema.md](references/result-schema.md). Then run:
```bash
python skills/llm-serving-auto-benchmark/scripts/compare_benchmark_results.py \
--input /path/to/candidates.jsonl \
--output /path/to/summary.md
```
Rank candidates in this order:
1. SLA passed
2. highest request throughput or goodput
3. highest output token throughput
4. lower p50 TTFT
5. lower p50 TPOT/ITL
6. lower GPU count or simpler deployment if performance is close
Keep the SLA gate itself unchanged. In the cookbook configs and normalized
result schema, TTFT SLA still uses `max_p50_ttft_ms` and TPOT SLA still uses
`max_p50_tpot_ms`; only the default cross-candidate comparison order switches
to p50 TTFT and p50 TPOT.
## Output Contract
Return a compact report with workload/SLA, hardware and framework versions, best
deployment-command tables per framework/scenario, one cross-framework comparison
table, exact launch and benchmark commands for winners, and artifact paths for
workload, raw/normalized results, CSV or markdown summary, and server logs.
When SGLang is not the winner, include a profiler handoff note with the slow
SGLang scenario name and the exact input/output lengths or percentile bucket to
pass to `llm-torch-profiler-analysis`.
When a candidate uses speculative decoding, prefix cache, offload, or an
agentic workload, record the optional normalized fields for accept length,
pre-scheduler time, cache hit rate, and memory residency. The summary script
will display those columns when present.
Include failed or excluded candidates with reasons. Explain that this table is a
record of tried configs that were not selected: candidates that failed, were
skipped by policy, or completed but missed the SLA. Add caveats for synthetic
workloads, incomplete fair searches, or framework-specific parameter
substitutions.
Use [references/framework-reference.md](references/framework-reference.md) when
you need command templates, source links, or knob-family mappings. Use
[references/example-plan.yaml](references/example-plan.yaml) as the starting
point for a full cross-framework run plan.
## Interface audit — 2026-10-05
SGLang's canonical client is `python -m sglang.benchmark.serving`; `bench_serving`
is a deprecated shim and the auto-benchmark module was removed (#31941). Capture
`sglang serve --help` and the client help from the target image. Current images
require CUDA 13 and a compatible host driver (#38404); the final CUDA 12 tag was
`v0.5.19-cu129`. MiniMax-M3 requires `lmsysorg/sglang:dev-minimax-m3`;
Qwen3.8-Flash-Next H200/B200 requires `lmsysorg/sglang:qwen38flashnext`.
Current SGLang uses phase-specific graph flags (#38375):
`--cuda-graph-backend-decode` / `--cuda-graph-backend-prefill` accept
`full`, `breakable`, `tc_piecewise`, `disabled`; capture sizes use
`--cuda-graph-bs-decode` / `--cuda-graph-bs-prefill` and
`--cuda-graph-max-bs-decode` / `--cuda-graph-max-bs-prefill`. Smoke eager mode is
`--cuda-graph-backend-decode disabled --cuda-graph-backend-prefill disabled`.
The old size aliases were removed and `--disable-cuda-graph` is deprecated.
`--attn-dp-size` replaces the old attention-DP pair on main (#41818);
`--dp-size` remains replica DP. v0.5.21 predates this spelling: inspect image help.
Also inspect `--attn-cp-size`, `--dcp-size`, `--moe-dp-size` and the `--ep` alias.
TensorRT-LLM at `bb367fc8` is PyTorch-only after #19028. `--backend pytorch`
is a deprecated compatibility option; omit it on current main and select it
only on older images whose help lists other backends. Both
`--free_gpu_memory_fraction` (primary) and `--kv_cache_free_gpu_memory_fraction`
(alias) work. The 1.0.0 image note is historical. `--cluster_size` is deprecated
and unsupported. `--set PATH=YAML_VALUE` can override config paths after `--config`.
TokenSpeed #1236 removed its benchmark subcommand. Use the common client
`vllm bench serve --backend openai-chat` for aligned workloads. `ts` remains
an alias for `tokenspeed`. The prefix-cache off switch is
`--disable-prefix-caching`; engine flags `--api-key`, `--enable-cache-report`,
`--skip-server-warmup`, `--warmups` were removed. `--tool-call-parser` and
`--chat-template` are gateway flags. Inspect `--pipeline-parallel-size`,
`--prefill-context-parallel-size`, `--decode-context-parallel-size`,
`--lm-head-tp-size` and `--dense-gemm-backend` when tuning parallelism.
Do not force vLLM `--block-size 16`: it excludes preferred MLA/DSA backends.
Let the backend select its block size, and record its startup dispatch line.
Use the same client version across compared rows: vLLM #55508 changed chat
TTFT/E2E chunk accounting, and SGLang #39889 reports server prompt-token usage
including template tokens. Record optional client queue latency separately.
The default SGLang scheduler is FCFS; historical cookbook YAMLs no longer
force LPM on random prompts. `False` for defaults-on booleans needs an explicit
off flag and must not silently duplicate the baseline. The YAML validator
requires Python 3.10 or newer.
Source evidence: [SGLang graph flags](https://github.com/sgl-project/sglang/blob/b1bbd74f287f13ed1276b0403a01ebb55c597e93/python/sglang/srt/arg_groups/fields/exec_.py),
[SGLang parallel flags](https://github.com/sgl-project/sglang/blob/b1bbd74f287f13ed1276b0403a01ebb55c597e93/python/sglang/srt/arg_groups/fields/parallel.py),
[vLLM backend sizing](https://github.com/vllm-project/vllm/blob/0c16eee3f1ff777298cc894c3eeb85f3880c6d6a/vllm/platforms/cuda.py),
[TensorRT-LLM serve](https://github.com/NVIDIA/TensorRT-LLM/blob/bb367fc8c1adf6e2c28c88cb1a8b46e1742a9d60/tensorrt_llm/commands/serve.py),
[TokenSpeed CLI](https://github.com/lightseekorg/tokenspeed/blob/6fa10840d5c3c23065f60428ad264fba60fa04ae/python/tokenspeed/cli/__main__.py).