 paulzhang-tm
|
463a3f4248
|
[Mamba] Support configurable conv-window layouts (#31059)
|
2026-07-14 14:41:10 -07:00 |
|
|
paulzhang-tm
|
08c46e1f1a
|
Add dummy forward batch preparation hook (#31070)
|
2026-07-14 14:30:31 -07:00 |
|
|
|
0d89564d27
|
Support scheduler_recv_interval (recv skipper) under DP-attention (#30457)
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
|
2026-07-14 14:02:58 -07:00 |
|
|
cctryandcctry
|
cb47a68717
|
[PD] Stride KV token->page indices on device before D2H copy (#31173)
Co-authored-by: cctry <cctry@fb.com>
|
2026-07-14 10:08:30 -07:00 |
|
|
hunhokimandHun-ho Kim
|
a5c3e0283f
|
[Bug fix] Account for KV replication fan-out in transfer-byte metrics (#30351)
Co-authored-by: Hun-ho Kim <hunho.kim@samsung.com>
|
2026-07-14 10:08:24 -07:00 |
|
|
Mick
|
04af94d150
|
fix: avoid tilelang cuda runtime pollution (#30870)
|
2026-07-14 22:30:27 +08:00 |
|
|
Peng Xingchen
|
f853293440
|
[NPU] Fix CPU device for node topology probe (#30619)
|
2026-07-14 22:17:54 +08:00 |
|
|
Ma Mingfei
|
31548781e0
|
[CPU] bypass scoring_func argument in topk for cpu device (#31110)
|
2026-07-14 21:48:22 +08:00 |
|
|
Kevin FlansburgandShangming Cai
|
bbb5702a3c
|
fix: avoid double KV release on disaggregated prefill grammar errors (#30937)
Co-authored-by: Shangming Cai <csmthu@gmail.com>
|
2026-07-14 20:16:58 +08:00 |
|
|
Mick
|
43241b7f3f
|
[diffusion] model: support fal Ideogram V4 Fast and Instant (#31177)
|
2026-07-14 19:51:35 +08:00 |
|
|
Xiaoyu ZhangandClaude Fable 5
|
ee000f6734
|
[CI] Fix SGLANG_JIT_KERNEL_RUN_FULL_TESTS never activating the nightly full jit-kernel sweep (#31042)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-14 17:32:29 +08:00 |
|
|
Xiaoyu ZhangandClaude Fable 5
|
1a35440c4a
|
[Kernel] Migrate generic attention kernels to sglang.kernels (RFC #29630, Phase 2.5, 4/7) (#30789)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-14 16:53:46 +08:00 |
|
|
fzyzcjy
|
0fe2dbd42c
|
Split initialize() into orchestration helpers (#31169)
|
2026-07-14 16:09:00 +08:00 |
|
|
Ankith Averineni
|
64a70c9097
|
[AMD] jit_kernel: complete utils.cuh HIP-compat (cudaDevAttr / cudaDeviceGetAttribute) (#31143)
|
2026-07-14 16:06:36 +08:00 |
|
|
fzyzcjy
|
bf04cc9b14
|
Extract cuda-graph setup into a module (#31168)
|
2026-07-14 16:04:45 +08:00 |
|
|
fzyzcjy
|
ed2fcd3201
|
Extract attention-backend setup into a module (#31167)
|
2026-07-14 16:03:48 +08:00 |
|
|
fzyzcjy
|
54f99a21d5
|
Narrow component dependencies to injected fields instead of ModelRunner (#31166)
|
2026-07-14 16:03:07 +08:00 |
|
|
fzyzcjy
|
6999007a13
|
Drop ModelRunner's duplicated parallel-degree fields and read them via self.ps (#31165)
|
2026-07-14 16:02:40 +08:00 |
|
|
fzyzcjy
|
cfd17301a8
|
Extract per-architecture KV-cache pool builders into KVCacheConfigurator (#31163)
|
2026-07-14 16:02:09 +08:00 |
|
|
fzyzcjy
|
d6cf2908ce
|
Introduce KVCacheConfigurator and migrate KV-cache config logic (#31162)
|
2026-07-14 16:01:45 +08:00 |
|
|
fzyzcjy
|
725920915f
|
Introduce ModelRunner.ps ParallelState (#31161)
|
2026-07-14 16:01:14 +08:00 |
|
|
fzyzcjy
|
1dc48c2c3b
|
Absorb capturer setup and extract the shared-mooncake gate (#31160)
|
2026-07-14 16:00:51 +08:00 |
|
|
fzyzcjy
|
08798dba0d
|
Extract MoE/EP setup into a moe_ep_setup module (#31159)
|
2026-07-14 16:00:24 +08:00 |
|
|
fzyzcjy
|
440aebdfe0
|
Extract small single-function helpers into modules (#31158)
|
2026-07-14 16:00:01 +08:00 |
|
|
fzyzcjy
|
17c04602c6
|
Extract spec aux-hidden-state resolution into a module (#31157)
|
2026-07-14 15:59:35 +08:00 |
|
|
fzyzcjy
|
39e508b7fc
|
Extract layer-index setup into a module (#31156)
|
2026-07-14 15:59:07 +08:00 |
|
|
fzyzcjy
|
5b540b16de
|
Extract load_model helpers into a load_model_utils module (#31155)
|
2026-07-14 15:58:40 +08:00 |
|
|
fzyzcjy
|
d15f6a9ac3
|
Introduce NgramEmbeddingManager component (#31154)
|
2026-07-14 15:58:08 +08:00 |
|
|
fzyzcjy
|
0f20f52e5e
|
Introduce RemoteInstanceWeightTransporter component (#31153)
|
2026-07-14 15:57:43 +08:00 |
|
|
fzyzcjy
|
caa85ea022
|
Extract init_torch_distributed and refactor into functions (#31152)
|
2026-07-14 15:56:57 +08:00 |
|
|
fzyzcjy
|
205a2f2de4
|
Move LoRA cuda-graph buffers and logging into LoRAManager (#31151)
|
2026-07-14 15:56:18 +08:00 |
|
|
fzyzcjy
|
e20c346541
|
Extract hybrid-arch helpers into configs.hybrid_arch and ModelConfig (#31150)
|
2026-07-14 15:55:32 +08:00 |
|
|
fzyzcjy
|
c9b4081016
|
Extract expert location updating into EPLBManager (#31149)
|
2026-07-14 15:54:40 +08:00 |
|
|
fzyzcjy
|
6507d4a090
|
Introduce WeightUpdater and WeightExporter components (#31148)
|
2026-07-14 15:53:33 +08:00 |
|
|
fzyzcjy
|
45dfa318fb
|
Extract kv cache dtype configuration into mem_cache (#31147)
|
2026-07-14 15:52:39 +08:00 |
|
|
fzyzcjy
|
cad8fe7a66
|
Extract leaf helpers out of ModelRunner into utility modules (#31146)
|
2026-07-14 15:52:03 +08:00 |
|
|
fzyzcjy
|
b1a60ad00d
|
Clean up ModelRunner by renaming effective-token property and remove dead code (#31145)
|
2026-07-14 15:50:53 +08:00 |
|
|
fzyzcjy
|
2cf753c4fe
|
Clarify ModelRunner.dp_size into attn_dp_size (#31142)
|
2026-07-14 15:49:05 +08:00 |
|
|
Zhanghengandispobock
|
afa3c06d1f
|
Using UnifiedRadixTree by default for SWA, Mamba, and DSA models (#30468)
Co-authored-by: ispobock <ispobaoke@gmail.com>
|
2026-07-14 15:17:08 +08:00 |
|
|
gjsheu
|
2ced88238a
|
[NPU] [BUGFIX] Fix input parameters of swiglu_oai operator (#30458)
|
2026-07-14 14:16:24 +08:00 |
|
|
|
702bddcee8
|
[Model] Add support for JetBrains' Mellum v2 code generation model (#27375)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Jiminator <69131491+Jiminator@users.noreply.github.com>
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
|
2026-07-13 22:54:38 -07:00 |
|
|
Yuxuan ZhangandBaizhou Zhang
|
7e229e2a81
|
support GLM-5.2 MTP index sharing with prefill CP (#30992)
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
|
2026-07-13 21:11:27 -07:00 |
|
|
cctry
|
1b4176cc46
|
[PD] Fix optimistic prefill inflight-queue hangs on parked/aborted reqs (#31075)
|
2026-07-13 20:34:44 -07:00 |
|
|
|
78dc581518
|
[bug-fix] Stabilize GLM-5.2 MTP IndexShare across PD and CUDA graph replay (#30839)
Co-authored-by: kpham-sgl <khoa.pham@radixark.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-13 19:37:07 -07:00 |
|
|
YAMY
|
41ad0d9c26
|
Allow prefill breakable CUDA graph for Qwen3.5 via multimodal opt-in allowlist (#30620)
|
2026-07-13 18:39:44 -07:00 |
|
|
|
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 |
|