sglang/benchmark at main - sglang - Gitea: Git with a cup of tea

mirrors/sglang

0 Fork 0

mirror of https://gitee.com/trusted-list/sglang.git synced 2026-10-28 08:34:56 +08:00

Files

T

History

+18

66f79f1a90 [Feat] kernels: Beam model support (#45254 )

Signed-off-by: Yoni Gozlan <yonigozlan@users.noreply.github.com>
Co-authored-by: BBuf <1182563586@qq.com>
Co-authored-by: Caihua Li <caihua.li@bytedance.com>
Co-authored-by: Florent Gbelidji <florentgbelidji@Florents-MacBook-Pro.local>
Co-authored-by: iaroslav-reflection <iaroslav@reflection.ai>
Co-authored-by: Jinze Xue <jinzex@nvidia.com>
Co-authored-by: mloh <mloh@nvidia.com>
Co-authored-by: neilkg <33635204+neilkg@users.noreply.github.com>
Co-authored-by: thibautbar <t.barroyer@icloud.com>
Co-authored-by: Florent Gbelidji <florent@reflection.ai>
Co-authored-by: Florent Gbelidji <florentgbelidji@florents-macbook-pro1.home>
Co-authored-by: Florent Gbelidji <florentgbelidji@Host-002.lan>
Co-authored-by: Jiajun Li <jiajun.li@radixark.ai>
Co-authored-by: Kaiwu <kai@reflection.ai>
Co-authored-by: Neil Gollapudi <neil@reflection.ai>
Co-authored-by: Qiaolin-Yu <liin1211@outlook.com>
Co-authored-by: Renault Young <renault@reflection.ai>
Co-authored-by: Yoni Gozlan <yoni@reflection.ai>
Co-authored-by: zhihengy <andy.ye@radixark.ai>
Co-authored-by: AymenKallala <aymen.kallala@gmail.com>
Co-authored-by: Florent Gbelidji <florentgbelidji@Mac.lan>
Co-authored-by: Jinze Xue <155670984+jinzex@users.noreply.github.com>
Co-authored-by: mreso <13337103+mreso@users.noreply.github.com>
Co-authored-by: Yanbin Jiang <jybsuper@gmail.com>
Co-authored-by: Yoni Gozlan <yonigozlan@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Yoni Gozlan <74535834+yonigozlan@users.noreply.github.com>

2026-10-26 12:28:56 -07:00

..

agentic-rollout

[Benchmark] Add agentic rollout simulator and offline explorer (#40034 )

2026-09-18 10:06:13 -07:00

[CI][RFC] Replace black-jupyter with ruff-format (#37210 )

2026-09-02 19:46:08 -07:00

bench_attention_sink

[Kernel] Introduce sglang.kernels namespace and migrate scattered triton_ops kernels (RFC #29630 , Phase 2) (#30044 )

2026-07-10 21:41:08 +08:00

bench_linear_attention

[Refactor] kernels: Regroup operators by computation and dissolve ops/muse_spark (#45112 )

2026-10-20 08:47:57 +08:00

bench_pynccl_allocator

Refactor: decouple segment tracking from comm registration (#21392 )

2026-05-06 17:07:58 +08:00

Remove smoke wording from tests and comments (#23355 )

2026-04-28 12:05:27 +08:00

Add Lychee Doc Links Check to Local and CI (#19742 )

2026-03-24 13:48:26 -07:00

[NPU]TP Communications compression For Qwen3 models for NPU (#20520 )

2026-05-02 14:29:11 +03:00

[Feature] Add --attn-dp-size and deprecate --enable-dp-attention (#41818 )

2026-09-30 13:34:18 -07:00

[PD] Bound cached-prefix DCP transfers by pack capacity (#40376 )

2026-09-21 01:17:15 +08:00

[dLLM] feat: support DiffusionGemma serving (#34061 )

2026-09-23 09:59:31 +08:00

[Kernel] Relocate vendored fla and mamba kernel trees to sglang.kernels (RFC #29630 , Phase 2.5, 7/7) (#30795 )

2026-07-15 12:52:15 +08:00

[Benchmark] Remove 22 unmaintained benchmarks (#34520 )

2026-08-11 22:24:43 -07:00

Check the topology identities where the layout is written, and build at the published widths (#40340 )

2026-09-21 12:22:59 -07:00

[ROCm] Eliminate HiCache migration stalls and use exact-size host allocations (#42553 )

2026-10-12 14:05:51 -07:00

[MM] Keep scheduler padding in packed token arrays (#40357 )

2026-09-22 15:12:07 -07:00

[Feat] kernels: Beam model support (#45254 )

2026-10-26 12:28:56 -07:00

Replace time.time() to time.perf_counter() for benchmarking. (#6178 )

2025-05-11 14:32:49 -07:00

benchmark/lora: make number of LoRA adapters configurable (#25363 )

2026-05-20 18:23:13 -07:00

[Cleanup] Deduplicate kernel tests, diffusion fixtures and benchmark helpers (#40265 )

2026-09-19 19:45:38 +08:00

[CI][RFC] Replace black-jupyter with ruff-format (#37210 )

2026-09-02 19:46:08 -07:00

[Score API] Setwise Scoring Support (#38965 )

2026-09-24 16:50:58 -07:00

[CI][RFC] Replace black-jupyter with ruff-format (#37210 )

2026-09-02 19:46:08 -07:00

Fix dataclasses.asdict on the msgspec ServerArgs (#38958 )

2026-09-10 17:22:54 -07:00

[unified-memory] Stop eviction when shared allocation capacity is sufficient (#33091 )

2026-08-26 02:06:32 -07:00

[Speculative Decoding] Add native UNO serving support (#37667 )

2026-09-03 20:08:41 +08:00

bench_adaptive_speculative.py

[SPEC][1/N] feat: add adaptive speculative_num_steps for EAGLE topk=1 (#21599 )

2026-04-20 14:25:04 -07:00

lean_kernel_sweep.py

[CI][RFC] Replace black-jupyter with ruff-format (#37210 )

2026-09-02 19:46:08 -07:00