Cheng Wan
729081e14f
docs: rewrite the runtime-context skill for the namespace-bag config model ( #33173 )
...
The skill still described the retired resolve-at-end contract (a single
resolved ServerArgs as the source of truth, ServerArgs.override as the
mutation entry). Rewrite the config sections for the landed model:
- ServerArgs is a pristine published seed; resolved config lives in the
namespace bags (get_exec()/get_memory()/.../get_device()), projected at
publish(server_args, role=...) per process entry.
- Post-publish mutation goes through get_context().override (bag-only);
ServerArgs.override is being retired behind the writer ratchet, and
rerouting a writer co-flips all its readers in the same commit.
- Documented the reads that stay on an instance (per-runner fork fields,
per-instance tokenizer/entrypoints boundaries, whole-object passes),
get_parallel()'s config/live dual semantics with the live-shadowed
sizes rule, preserve_config for nested publishes, and the bag-only
declare_load_time_override route.
- Testing idioms: publish-seeding (override_server_args + scoped bag
overrides) instead of faking accessors or SimpleNamespace stand-ins;
per-file test runs to avoid leaked-publish masking.
- Guardrails: added the writer ratchet, namespace-coverage lint, and the
migration-deferral ratchet.
2026-08-01 09:00:10 -07:00
e4c4faf8a2
feat(cookbook): add DGX Spark support for Inkling-Small ( #33131 )
...
Co-authored-by: Zijie Xia <zijie.xia@radixark.ai >
Co-authored-by: Claude Opus 5 <noreply@anthropic.com >
2026-08-01 00:25:25 +00:00
DarkSharpness and Claude Fable 5
3abbc565e4
[Docs] Add a Conventions section to the add-jit-kernel skill ( #32956 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com >
2026-07-31 09:11:49 +08:00
Ke Bao
3763d3fa8c
Add decode-lock skip to compute-mamba-ratio ( #32789 )
2026-07-29 22:38:34 +08:00
Ke Bao
c151080d28
Add compute-mamba-ratio skill ( #32763 )
2026-07-29 18:15:48 +08:00
Xiaoyu Zhang
c32c4ef79c
[Kernel] Move sgl-kernel under sglang.kernels.aot ( #32648 )
2026-07-29 17:25:00 +08:00
Yuhao Yang
7cae831e41
Update mi35x ROCm image to k3-20260727 ( #32559 )
2026-07-27 10:52:41 -07:00
7dafacca49
docs(cookbook): add the Kimi-K3 serving cookbook ( #32542 )
...
Co-authored-by: kpham-sgl <khoa.pham@radixark.ai >
Co-authored-by: Zijie Xia <zijie.xia@radixark.ai >
Co-authored-by: ispobock <ispobaoke@gmail.com >
Co-authored-by: Mick <mickjagger19@icloud.com >
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com >
Co-authored-by: thomawan <thomawan@amd.com >
Co-authored-by: BBuf <1182563586@qq.com >
2026-07-27 08:37:30 -07:00
Xiaoyu Zhang and Claude Opus 4.8
11b0e5c5ad
[Kernel] Classification cleanup: unify _jit_ naming, drop empty/model groups, add elementwise (RFC #29630 ) ( #32148 )
...
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com >
2026-07-23 13:47:02 +08:00
Xiaoyu Zhang and Claude Opus 4.8
99f636a86f
[Kernel] RFC #29630 finale: retire sglang.jit_kernel into sglang.kernels ( #32072 )
...
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com >
2026-07-23 08:35:09 +08:00
4a55fdba0b
docs(cookbook): re-benchmark DeepSeek-V4 on sglang 0.5.15 ( #31363 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
Co-authored-by: Zijie Xia <zijie.xia@radixark.ai >
2026-07-21 22:55:36 +00:00
67e7f8d13a
[JIT] Refactor dtype traits into DTypeTrait and unify warp reductions ( #30838 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com >
Co-authored-by: BBuf <xiaoyu.zhang@radixark.ai >
Co-authored-by: jessiewei7 <jessiewei747@gmail.com >
Co-authored-by: root <root@GPUC5A6.maas >
2026-07-18 10:07:18 +08:00
zijiexia
1b9f228838
[Docs] Playground: migrate CP knob to canonical prefill-CP flags, align gating with runtime semantics ( #31411 )
2026-07-16 01:07:34 -07:00
Артем Савкин and ronnie_zheng
8ed82afcc8
[MoE Refactor] [NPU] Refactor Ascend MoE implementation to reduce code duplication and align with community design ( #25663 )
...
Co-authored-by: ronnie_zheng <zl19940307@163.com >
2026-07-15 14:59:42 +03:00
fzyzcjy
52a88fb212
Avoid mutating ScheduleBatch fields in place ( #30672 )
2026-07-15 14:27:08 +08:00
fzyzcjy
e77d95c3d5
Pass per-forward overrides to ForwardBatch.init_new as explicit arguments ( #30670 )
2026-07-15 14:25:59 +08:00
fzyzcjy
a5a71c6c26
Enhance mechanical-refactor-verify skill with a whole-chain verifier, new relocation primitives, and generator inference ( #30585 )
2026-07-14 16:45:48 +08:00
zijiexia
50ed4c011f
Remove legacy Sphinx docs/ and finish the Mintlify cutover ( #28964 )
2026-07-13 15:06:08 -07:00
Liangsheng Yin
e2728ac504
[Spec] Remove dead padded_static_len and stale SGLANG_ENABLE_SPEC_V2 references ( #30998 )
2026-07-13 15:30:31 -05:00
Liangsheng Yin
a36c873147
[misc] Remove unit test cases that fail the admission criteria (round 2) ( #30703 )
2026-07-09 16:35:59 -07:00
Liangsheng Yin
c46b291c77
[misc] Add init-static value extraction to the general code style rule ( #30701 )
2026-07-09 15:25:53 -07:00
Cheng Wan
d8791fb5e3
[docs] Add the sglang-runtime-context skill ( #30494 )
2026-07-09 02:11:36 -07:00
Liangsheng Yin
9e4483d725
[misc] Add unit test admission criteria to agent rules ( #30608 )
2026-07-08 23:41:48 -07:00
fzyzcjy
bc607ff650
Enhance mechanical refactor proof construction and verification skill ( #30483 )
2026-07-09 07:39:11 +08:00
fzyzcjy
6af1d5ff2d
Enhance large class styles and code styles ( #28978 )
2026-07-09 07:32:03 +08:00
zijiexia and Claude Opus 4.8
7c9bb316cf
docs(cookbook): total (input+output) throughput per GPU + percentile latency labels ( #30214 )
...
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com >
2026-07-06 00:39:48 -07:00
Lianmin Zheng
1a5977d41b
[chore] Add no-getattr rule; refine no-dataclasses rule ( #29871 )
2026-07-01 15:31:34 -07:00
3e16be2122
[CI] Migrate JIT tests to runner config registration ( #29066 )
...
Co-authored-by: Cursor <cursoragent@cursor.com >
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-29 19:12:14 -07:00
Xiaoyu Zhang
c36f166364
[skill] Remove outdated llm-serving-auto-benchmark skill ( #29487 )
2026-06-27 14:19:11 +08:00
zijiexia and Claude Opus 4.8
dd56a9f069
[Docs] Add NVFP4 quantization to GLM-5.2 cookbook ( #29380 )
...
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com >
2026-06-26 00:40:13 -07:00
Lianmin Zheng
d331fdd2ba
Add project rule: prefer msgspec.Struct over dataclasses ( #28816 )
2026-06-20 18:43:16 -07:00
Xiaoyu Zhang
b6be5dd20f
[codex] Remove outdated SGLang SOTA skill ( #28719 )
2026-06-19 16:26:44 +08:00
zijiexia and Claude Opus 4.8
7221be2cec
feat(cookbook): MTP --max-running-requests callout + skill sync ( #28340 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-15 15:53:01 -07:00
DarkSharpness and Claude
cc72e2bd8c
[Docs] Fix outdated benchmark marker API in add-jit-kernel skill ( #27773 )
...
Co-authored-by: Claude <noreply@anthropic.com >
2026-06-13 23:47:30 -07:00
zijiexia and Claude Opus 4.8
d988d5d681
feat(cookbook): generic config-declared flagSelects playground axis ( #28128 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-13 11:46:34 -07:00
zijiexia and Claude Fable 5
29ac249be1
docs: add cookbook-migrate-model skill from the Qwen3.5 pilot ( #27845 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com >
2026-06-12 18:31:52 -07:00
Liangsheng Yin
c0480a88be
[Spec] Retire Spec V1 ( #27964 )
2026-06-11 16:15:15 -07:00
zijiexia and Claude Fable 5
43835b5ba5
docs: cookbook benchmark accuracy labels come from the model config (no engine default) ( #27842 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com >
2026-06-10 18:27:38 -07:00
zijiexia and Claude Fable 5
73d0989d9b
docs: make playground issue template model field a free-form input ( #27827 )
...
Co-authored-by: Claude Fable 5 <noreply@anthropic.com >
2026-06-10 14:04:16 -07:00
zijiexia and Claude Opus 4.8
99258b2f1e
[Docs] Restore right-hand ToC on the DeepSeek-V4 cookbook page ( #27830 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-10 11:58:02 -07:00
zijiexia
6565b7c464
[Docs] Update MegaMoE handling and rerun benchmarks ( #27726 )
2026-06-09 19:00:43 -07:00
Liangsheng Yin
186f1e300a
[CI] Move JIT kernel tests + benchmarks to test/registered/jit; add in-package guard ( #27644 )
2026-06-09 12:37:39 -07:00
zijiexia and Claude Opus 4.8
d1777d1f6d
Cookbook renovation ( #26885 )
...
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-07 22:04:54 -07:00
fzyzcjy
dd176387c6
Add scripted-runtime harness core and wire scheduler/IPC hooks ( #27411 )
2026-06-06 09:07:01 +08:00
Liangsheng Yin
f143d54d78
Add env-var-conventions skill ( #26553 )
2026-05-28 02:58:37 -07:00
DarkSharpness and Claude Opus 4.7
8f21b3e2ef
[Refactor] JIT kernel benchmark ( #25274 )
...
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com >
2026-05-28 00:49:55 -07:00
Alison Shao
5018e5c969
[CI] /rerun-test: support glob wildcard patterns ( #26422 )
2026-05-27 21:55:58 -07:00
fzyzcjy
d9c82934c8
Extract Scheduler init methods and add skills to enforce the splitting requirements ( #26271 )
2026-05-26 17:45:09 +08:00
fzyzcjy
b0cf01eb85
Lazy-load speculative-naming via skill instead of always-on rule ( #26270 )
2026-05-25 15:58:29 +08:00
Lianmin Zheng
93fa577bb9
Clean up server startup log noise ( #26205 )
2026-05-24 14:35:15 -07:00
Cheng Wan