Files

Uranus 982db4ebac Feat: GLM-4.6 supports shared experts fusion (#13873 )

Signed-off-by: UranusSeven <109661872+UranusSeven@users.noreply.github.com>
Co-authored-by: Kevin-XiongC <kevin_xiong1997@outlook.com>
Co-authored-by: Mingyi Jin <jinmingyi1998@sina.cn>

2025-12-01 11:33:18 +08:00

cli

fix: fix serve command without diffusion dependency (#13246 )

2025-11-14 10:24:18 +08:00

eval

…

jit_kernel

[Feature] HiCache JIT kernel (once again) (#13764 )

2025-11-22 22:19:16 -08:00

lang

Remove unused code / testcases in lang (#13335 )

2025-11-16 22:48:35 +08:00

multimodal_gen

[diffusion] lora: Fix LoRA weight merging for torch.nn.Linear layers from diffusers modules (#14150 )

2025-11-30 12:44:12 +08:00

srt

Feat: GLM-4.6 supports shared experts fusion (#13873 )

2025-12-01 11:33:18 +08:00

test

feat: Naive support Spec V2 + Constrained Decoding (#13425 )

2025-11-27 20:31:46 +08:00

__init__.py

…

bench_offline_throughput.py

test: support return logprobs in bench_offline_throughput test (#12462 )

2025-11-03 21:38:48 -08:00

bench_one_batch_server.py

Fix condition for streaming output_ids in tokenizer manager (#13759 )

2025-11-29 13:56:15 -08:00

bench_one_batch.py

[DP-Attn] Clarify MLP sync / idle batch preparation logic (#12843 )

2025-11-08 23:23:14 +08:00

bench_serving.py

[GLM4.6v] Required changes for bumping up to transformer 5.x (#13229 )

2025-11-18 10:58:00 +08:00

check_env.py

[NPU] chore: bump to CANN 8.3.RC1 and Pytorch 2.8.0 (#13647 )

2025-11-21 17:07:08 +08:00

compile_deep_gemm.py

fix: dummy health check server not accessible on non-zero rank nodes (#12297 )

2025-10-31 11:34:57 -07:00

global_config.py

Depreate global_server_args_dict (#11528 )

2025-10-13 19:34:43 +08:00

launch_server.py

WIP: initial multimodal-gen support (#12484 )

2025-11-05 12:28:52 -08:00

profiler.py

[Auto Sync] Improve profilers and simplify bench_one_batch_server.py (#13866 )

2025-11-25 12:13:31 -08:00

README.md

fix typo of args description in sglang.profiler (#12486 )

2025-11-04 20:15:13 -08:00

utils.py

perf: optimize TypeBasedDispatcher using dict for O(1) lookup (#12001 )

2025-11-15 22:02:42 +08:00

version.py

chore: bump SGLang version to 0.5.5.post3 (#13366 )

2025-11-16 17:55:38 -08:00

README.md

Code Structure

eval: The evaluation utilities.
lang: The frontend language.
srt: The backend engine for running local models. (SRT = SGLang Runtime).
test: The test utilities.
api.py: The public APIs.
bench_offline_throughput.py: Benchmark the performance in the offline mode.
bench_one_batch.py: Benchmark the latency of running a single static batch without a server.
bench_one_batch_server.py: Benchmark the latency of running a single batch with a server.
bench_serving.py: Benchmark online serving with dynamic requests.
check_env.py: Check the environment variables and dependencies.
global_config.py: The global configs and constants.
launch_server.py: The entry point for launching a local server.
profiler.py: The profiling entry point to send profile requests.
utils.py: Common utilities.
version.py: Version info.