|
7431f35fd8
|
Delete CUTLASS FP8 blockwise for SM90 and SM100, move SM120 to JIT and add SwapAB (#30438)
Co-authored-by: Brayden Zhong <brayden.zhong@radixark.ai>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: root <root@sgl-b300-inference.datacrunch.io>
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
|
2026-07-14 09:31:32 +08:00 |
|
|
Brayden Zhongandroot
|
9756f768a6
|
Refactor FP4 quantization and remove deprecated JIT kernels (#30448)
Co-authored-by: root <root@sgl-b300-inference.datacrunch.io>
|
2026-07-14 09:22:07 +08:00 |
|
|
|
0c01971eeb
|
[Intel GPU] DeepSeek V4 9/N: use sgl-kernel implementation of hadamard_transform on XPU (#28046)
Co-authored-by: Rahul Vijayaraghavan <rahul.vijayaraghavan@intel.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
|
2026-07-14 09:21:31 +08:00 |
|
|
Xiaoyu ZhangandClaude Fable 5
|
e9ef06c560
|
[Kernel] Migrate top-level srt/layers stray kernels to sglang.kernels (RFC #29630, Phase 2.5, 3/7) (#30787)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-14 09:20:59 +08:00 |
|
|
Polisetty V R K Jyothendra Varma
|
e489685509
|
[Intel GPU] DeepSeek V4 5/N: Use sgl-kernel implementation of fused_q_indexer_rope_hadamard_quant to run on XPU (#27873)
Signed-off-by: P V R K Jyothendra Varma <polisettyvarma@gmail.com>
|
2026-07-14 09:20:50 +08:00 |
|
|
Xiaoyu ZhangandClaude Fable 5
|
ee464fedc6
|
[Kernel] Migrate scattered MoE kernels to sglang.kernels (RFC #29630, Phase 2.5, 2/7) (#30786)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-14 09:03:21 +08:00 |
|
|
Mick
|
33f83011e0
|
fix: fix Kimi-VL encoder parallelism (#30869)
|
2026-07-14 08:44:06 +08:00 |
|
|
|
423b8485fb
|
[Quantization] add humming quantization kernel (#23754)
Co-authored-by: guzekai01 <zekai01@antgroup.com>
Co-authored-by: Julian Huang <huangzhilin.hzl@gmail.com>
Co-authored-by: 墨楼 <huangzhilin.hzl@antgroup.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Peng Zhang <aniz1905@gmail.com>
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>
|
2026-07-14 08:42:56 +08:00 |
|
|
|
cfe4eefabb
|
[diffusion] model: support LongLive 2.0 T2V and I2V inference (#27639)
Co-authored-by: Yihao Wang <42559837+AgainstEntropy@users.noreply.github.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
|
2026-07-13 17:39:30 -07:00 |
|
|
Mohammad Miadh Angkad
|
2f79d334f2
|
[Bugfix] Fix DeepSeek ForwardFlags across custom op boundary (#30987)
|
2026-07-13 17:19:44 -07:00 |
|
|
Po-Han Huang (NVIDIA)
|
cfc3d0555e
|
Fix ModelOpt NVFP4 scalar scales for merged linears (#29151)
|
2026-07-13 16:14:20 -07:00 |
|
|
hari-hm
|
a909077d22
|
Return top-p/top-k sampling mask/nucleas (#27408)
|
2026-07-13 17:58:51 -05:00 |
|
|
Brayden Zhong
|
0ee236ebdf
|
more fixes for Nemotron 3 parser for tool call and force nonempty content (#30533)
|
2026-07-14 06:50:27 +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 |
|
|
Jialin Ouyang
|
47030b28be
|
Fix MockDSV4ModelRunner missing spec_algorithm (#31056)
|
2026-07-13 15:24:28 -05:00 |
|
|
Liangsheng Yinandronhuafeng
|
2ab531cfcf
|
fa3/fa4: sync-free for all backends and phases (#29589)
Co-authored-by: ronhuafeng <ronhuafeng@users.noreply.github.com>
|
2026-07-13 15:09:57 -05:00 |
|
|
Khoa Pham
|
f49cbbd67d
|
Fix GLM/DeepSeek NVFP4 + flashinfer_trtllm long-context "!!!!" collapse (NaN routing) (#31001)
|
2026-07-13 12:54:38 -07:00 |
|
|
Yuwei An
|
86c59ac1aa
|
Revert "[Tiny] Enable Full Cuda Graph with Page size = 1" (#31062)
|
2026-07-13 14:23:44 -05:00 |
|
|
Liangsheng Yin
|
48fff1f2bd
|
[Spec] Deduplicate spec-v2 worker lifecycle boilerplate into BaseSpecWorker (#31008)
|
2026-07-13 13:48:40 -05:00 |
|
|
Liangsheng Yin
|
c0f1f7e062
|
[Spec] Rename num_tokens_per_bs to num_tokens_per_req (#30977)
|
2026-07-13 13:47:53 -05:00 |
|
|
|
11a82af5f8
|
[Platform] Route pin memory availability through current_platform (#28113)
Co-authored-by: N3u0ns <N3u0ns@users.noreply.github.com>
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
|
2026-07-13 11:37:59 -07:00 |
|
|
Xinyuan Tong
|
afaa17a7f2
|
[Feature] Add --default-chat-template-kwargs server arg (#29579)
|
2026-07-13 11:34:39 -07:00 |
|
|
Yuwei AnandClaude Fable 5
|
b44ac5d49a
|
[Tiny] Enable Full Cuda Graph with Page size = 1 (#30835)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-14 01:07:02 +08:00 |
|
|
ziruiliu
|
978bce2063
|
[HiCache & HybridModel] nixl hicache backend support hybrid models (#29191)
Signed-off-by: Zirui Liu <ziliu@ddn.com>
|
2026-07-13 09:09:37 -07:00 |
|
|
Ziang Li
|
2cf2920d07
|
[FlashInfer v0.6.13] Use CuTe DSL backend for FlashInfer per-token NVFP4 quantization (#28220)
|
2026-07-13 22:37:46 +08:00 |
|
|
|
9fec359a60
|
[Fix] Load HunyuanV3 NextN final_layernorm into the draft head's output norm (#30331)
Co-authored-by: Auroter <auroter@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-13 20:37:36 +08:00 |
|
|
Yichao Cheng
|
a74bee2261
|
[PD] Handle NIXL abort notifications (#30352)
|
2026-07-13 05:05:25 -07:00 |
|
|
xutizhou
|
eb31b5310c
|
Support Waterfill with MegaMoE backend (#27350)
|
2026-07-13 03:56:46 -07:00 |
|
|
Xiaoyu ZhangandClaude Fable 5
|
874fc07d9b
|
[Kernel] Migrate scattered quantization kernels to sglang.kernels (RFC #29630, Phase 2.5, 1/7) (#30784)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-13 16:17:01 +08:00 |
|
|
|
08d6d297e5
|
[Bugfix][NPU] Fix Hunyuan3 model where MoE's routing_scaling_ratio is missing on NPU (#29909)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Even Zhou <even.y.zhou@outlook.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
|
2026-07-13 09:48:41 +03:00 |
|
|
Baizhou Zhang
|
82e7cdcff9
|
[Misc] Remove a few dead code paths in DSA (#30973)
|
2026-07-12 23:25:03 -07:00 |
|
|
shuwenn
|
9dd57ef8c4
|
[mem_cache][7/N] refactor: move MLATokenToKVPoolHost to pool_host.mla (#30616)
|
2026-07-13 14:23:38 +08:00 |
|
|
Mohammad Miadh Angkad
|
cbcbef6811
|
[Bugfix] Fix Nemotron ForwardFlags across custom op boundary (#30968)
|
2026-07-12 22:10:23 -07:00 |
|
|
yz-wqf
|
4cec9ef9d7
|
[Fix] Forward on_after_cuda_graph_warmup through HybridLinearAttnBackend (#30846)
|
2026-07-13 09:40:52 +08:00 |
|
|
Lianmin ZhengandLu Fang
|
22c08a9bee
|
Preserve RMSNorm shape in batch-invariant mode (#30956)
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
|
2026-07-12 17:51:53 -07:00 |
|
|
Mick
|
7da30f4e55
|
feat: enable piecewise prefill graph for Kimi K2.5/K2.7 (#30889)
|
2026-07-13 08:37:30 +08:00 |
|
|
Lianmin Zheng
|
b94ac87e0c
|
Enable breakable prefill CUDA graph for DP attention (#30898)
|
2026-07-12 17:10:04 -07:00 |
|
|
cctry
|
c616d5a55e
|
[PD] Improve optimistic prefill (#30951)
|
2026-07-12 15:31:53 -07:00 |
|
|
|
6cc9352dfe
|
[Spec] Add DSpark: confidence-scheduled speculative decoding (#30261)
Co-authored-by: sglang-bot <232288953+sglang-bot@users.noreply.github.com>
Co-authored-by: Claude Code <noreply@anthropic.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
|
2026-07-12 17:25:26 -05:00 |
|
|
Liangsheng Yin
|
5ba3c5147e
|
[Spec] Add kill-switch env for draft-extend CUDA graph capture (#30944)
|
2026-07-12 14:54:36 -05:00 |
|
|
Lianmin ZhengandJialin Ouyang
|
539253e1d5
|
Gate Rust extension builds (#30927)
Co-authored-by: Jialin Ouyang <jialino@meta.com>
|
2026-07-12 05:44:58 -07:00 |
|
|
Yonghao Zhuang
|
80856aba85
|
Make the mxfp8 MoE runner backend list extensible (#30828)
|
2026-07-12 01:28:10 -07:00 |
|
|
Lianmin ZhengandYongji Wu
|
81d273f73b
|
Handle coredump dirs and cache hit updates (#30897)
Co-authored-by: Yongji Wu <30348494+libertyeagle@users.noreply.github.com>
|
2026-07-12 00:37:43 -07:00 |
|
|
Mick
|
f1c247edf9
|
profile: add vlm prefill profiler ranges (#30871)
|
2026-07-12 14:07:10 +08:00 |
|
|
Mick
|
bce3fc987d
|
perf: reuse MoonViT FA3 max-seqlen metadata (#30878)
|
2026-07-12 14:05:21 +08:00 |
|
|
Mick
|
a358abd651
|
chore: update vlm moe config and tune scripts (#30866)
|
2026-07-12 08:35:59 +08:00 |
|
|
Mohammad Miadh Angkad
|
14bef7cd11
|
fix: lazy load TileLang MHC kernels (#30580)
|
2026-07-12 08:32:27 +08:00 |
|
|
Mick
|
af66370d81
|
bench: support random image resolutions (#30879)
|
2026-07-12 08:28:56 +08:00 |
|
|
Liangsheng Yin
|
4884f6fbee
|
[Fix] Unify ForwardBatch extend lens cpu fields to their declared list type (#30896)
|
2026-07-11 17:30:53 -05:00 |
|