Papers › SGLang: Efficient Execution of Structured Language Model Programs

SGLang: Efficient Execution of Structured Language Model Programs

12 Dec 2023arXiv:2312.07104archive 2025-07-28

Lianmin Zheng, Liangsheng Yin, Zhiqiang Xie, Chuyue Sun, Jeff Huang, Cody Hao Yu, Shiyi Cao, Christos Kozyrakis, Ion Stoica, Joseph E. Gonzalez, Clark Barrett, Ying Sheng

Large language models (LLMs) are increasingly used for complex tasks that require multiple generation calls, advanced prompting techniques, control flow, and structured inputs/outputs. However, efficient systems are lacking for programming and executing these applications. We introduce SGLang, a system for efficient execution of complex language model programs. SGLang consists of a frontend language and a runtime. The frontend simplifies programming with primitives for generation and parallelism control. The runtime accelerates execution with novel optimizations like RadixAttention for KV cache reuse and compressed finite state machines for faster structured output decoding. Experiments show that SGLang achieves up to 6.4x higher throughput compared to state-of-the-art inference systems on various large language and multi-modal models on tasks including agent control, logical reasoning, few-shot learning benchmarks, JSON decoding, retrieval-augmented generation pipelines, and multi-turn chat. The code is publicly available at https://github.com/sgl-project/sglang

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 17 code samples harvested from 2 repositories linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 1 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 7 ran (2 with no instrument failure; 5 where Syntology's instrument failed); community (archive-listed): 10 samples from 1 repository, 9 ran (7 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 16 samples that ran have no recorded date.

sgl-project/sglang officialmentioned in papermentioned on GitHubpytorchSyntology: 7 samples, 7 ran (5 instrument-failed) · 0 unverified report
tginart/sglang mentioned on GitHubpytorchApache-2.0Syntology: 10 samples, 9 ran (2 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

17 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 1 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
1ran · violated contract
6ran · our draft was wrong
1ran; the contract check could not run
5ran
1unverified

Licence: 0 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

sgl-project/sglang official repository 7 samples, 7 ran (5 instrument-failed) · 0 unverified
attention_pytorch benchmark/kernels/attention/bench_flash_attention_fp8.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 4afe00a5853d633f · report fixture: signature qkv:Tensor/5/float, causal:bool/0/bool · returned Tensor · level recorded 2026-09-22
efficiency benchmark/kernels/attention/bench_flash_attention_fp8.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · f29cb637db3ec374 · report fixture: signature flop:int/0/int, seconds:float/0/float · returned float · level recorded 2026-09-22
first_image_from_body docs/scripts/update_lmsys_sglang_blogs.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 50162116dff0fb49 · report fixture: signature body:str/0/str · returned str · level recorded 2026-09-22
flops benchmark/kernels/attention/bench_flash_attention_fp8.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · e73bdfbda28da341 · report fixture: signature batch:int/0/int, seqlen:int/0/int, headdim:int/0/int, nheads:int/0/int, causal:bool/0/bool · returned int · level recorded 2026-09-22
split_checkpoint_files examples/checkpoint_engine/update.py ran · our draft was wrong Apache-2.0 (permissive) · ae700d7ba09b1dad · report fixture: signature checkpoint_path:str/0/str, rank:int/0/int, world_size:int/0/int · returned list · level recorded 2026-09-22
split_frontmatter docs/scripts/update_lmsys_sglang_blogs.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · ccf4f09d98748ede · report fixture: signature content:str/0/str · returned tuple · level recorded 2026-09-22
to_absolute_url docs/scripts/update_lmsys_sglang_blogs.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 89728bc22a4636de · report fixture: signature url_or_path:str/0/str · returned str · level recorded 2026-09-22
tginart/sglang community (archive-listed) 10 samples, 9 ran (2 instrument-failed) · 1 unverified
contains_formats benchmark/json_schema/bench_sglang.py ran · violated contract Apache-2.0 (permissive) · c35d5a367cb5def6 · report fixture: signature schema:dict/0/?, formats:list/1/str · returned bool · level recorded 2026-09-26
format_example in 43 papers benchmark/mmlu/bench_sglang.py ran · our draft was wrong Apache-2.0 (permissive) · cd763eaf1ac287e7 · report fixture: signature df:DataFrame/0/?, idx:int/0/int, include_answer:bool/0/bool · returned str · level recorded, date not recorded
format_subject in 26 papers benchmark/mmlu/bench_sglang.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 6ab745408cb8648b · report fixture: signature subject:str/0/str · returned str · level recorded, date not recorded
gen_prompt in 35 papers benchmark/mmlu/bench_sglang.py ran Apache-2.0 (permissive) · c7131fbea2cbdc2d · report fixture: signature train_df:DataFrame/0/?, subject:str/0/str, k:int/0/int · returned str · level recorded 2026-09-26
get_answer_value benchmark/gsm8k/bench_sglang.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 4c13c3bdb761b46c · report fixture: signature answer_str:str/0/str · returned int · level recorded 2026-09-26
get_few_shot_examples benchmark/gsm8k/bench_sglang.py ran Apache-2.0 (permissive) · 9e0d3df1a2d9a123 · report fixture: signature lines:list/1/dict, k:int/0/int · returned str · level recorded 2026-09-26
get_few_shot_examples benchmark/hellaswag/bench_sglang.py ran Apache-2.0 (permissive) · 06681001174b0ca9 · report fixture: signature lines:list/1/dict, k:int/0/int · returned str · level recorded 2026-09-26
get_one_example benchmark/gsm8k/bench_sglang.py ran Apache-2.0 (permissive) · 2e994f473fac61f9 · report fixture: signature lines:list/1/dict, i:int/0/int, include_answer:bool/0/bool · returned str · level recorded 2026-09-26
get_one_example benchmark/hellaswag/bench_sglang.py ran Apache-2.0 (permissive) · 5b4a33e73835b337 · report fixture: signature lines:list/1/dict, i:int/0/int, include_answer:bool/0/bool · returned str · level recorded 2026-09-26
convert_dataset benchmark/json_schema/bench_sglang.py unverified Apache-2.0 (permissive) · abf01e5c788687e5 · report

Tasks

Few-Shot LearningLanguage ModelingLanguage ModellingLogical ReasoningRetrievalRetrieval-augmented Generationmodel

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SPEED

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections