This website requires JavaScript.
4b23f6bdc5
Fix performance regression on Deepseek V3 on moe-runner-backend=triton on SM90 (#24562 )
Brayden Zhong and b8zhong
2026-05-09 06:49:12 -04:00
05d1ab51e8
Enable PDL for various kernels in DSV32/GLM5 (#23965 )
Brayden Zhong and b8zhong
2026-05-09 06:42:56 -04:00
d5564c2a96
fix(fa3): translate page table to SWA loc in EAGLE3 topk>1 spec metadata (#24617 )
shuwenn
2026-05-09 18:22:45 +08:00
a309f1f8f4
fix(cuda_graph): zero out_cache_loc_swa on pad and use int32 (hybrid-SWA accuracy fix) (#24743 )
JoyFuture
2026-05-09 18:22:12 +08:00
ba625d5290
slash command rerun UX: emoji semantics + result writeback (#24802 )
Liangsheng Yin
2026-05-09 03:19:24 -07:00
f4b7e73699
Enable trtllm-gen BF16 MoE for MTP (#24260 )
Brayden Zhong and b8zhong
2026-05-09 06:14:17 -04:00
f1a9a455e0
Revert "[NPU] fix profiler on npu" (#24815 )
sglang-npu-bot
2026-05-09 17:53:02 +08:00
e2527df8b6
[NPU] fix profiler on npu (#24685 )
zhaozx-cn
2026-05-09 17:48:24 +08:00
fd636410a2
Restrict fa_skip_kv_cache to non-MLA backends (#24097 )
Jia Guo
2026-05-09 02:25:02 -07:00
8f33bee31b
Reland Cute-DSL FP4 dense GEMM (#23590 )
Brayden Zhong and b8zhong
2026-05-09 05:20:58 -04:00
d49fc092cb
[Bug Fix] GLM-5.1: drop constexpr on page_indice_batch_offset, skip offloader post_init on draft worker, support N=32 in copy_to_gpu_no_ce (#23550 )
Yuxuan Zhang
2026-05-09 09:43:45 +02:00
9d12f9e6fa
[HiCache] ci: lower est_time for test_hicache_spec_file_storage (#24713 )
shuwenn and Claude Opus 4.7
2026-05-09 15:33:18 +08:00
78da0d3106
[Spec] Move accept_tokens off EagleDraftInput; pass via method arg (#24735 )
Liangsheng Yin
2026-05-08 23:24:18 -07:00
1610aa77ab
Reduce gemma4 moe deterministic test runtime (#24754 )
Khoa Pham
2026-05-08 20:46:56 -07:00
8e534e8f15
[diffusion] fix: fix diffusers executor crash when component residency manager is absent (#24573 )
Chi McIsaac
2026-05-08 23:45:06 -04:00
44a527f6f4
fix patch_torch test queue race (#24739 )
Liangsheng Yin
2026-05-08 20:25:59 -07:00
590b13b513
[diffusion] fix: fix NCCL deadlock in ulysses sp when sequence length has remainder (#24694 )
storyicon
2026-05-09 11:05:37 +08:00
50ed01674e
fix is_arch_support_pdl function usage (#24600 )
Polisetty V R K Jyothendra Varma and Ma Mingfei
2026-05-09 07:09:34 +05:30
1613bae412
[Spec] Disambiguate verified_id into bonus_token(s) / accept_tokens (#24724 )
Liangsheng Yin
2026-05-08 18:24:33 -07:00
a61a14f416
[KDA] Optimize prefill kernels with diagonal and recompute fuse (#24271 )
Yuan Luo and luoyuan.luo
2026-05-09 08:52:51 +08:00
9ee830346f
Disable Custom AR V2 when in multi-node (#24729 )
Brayden Zhong and b8zhong
2026-05-08 20:50:05 -04:00
d1c5937428
env: add SGLANG_RADIX_FORCE_MISS to force radix prefix-cache miss (#24726 )
2026-05-08 17:46:38 -07:00
560829a171
feat(scheduler): add adaptive queue-based prefill delayer trigger (#23189 )
YAMY
2026-05-08 16:54:30 -07:00
6971a03fe6
fix(fa3): skip scheduler_metadata precompute under DP attention (#24632 )
YAMY
2026-05-08 16:19:20 -07:00
62c2e091f6
[PD] MORI-IO: Add state transfer, inline transfer model, and high-concurrency fixes (#22665 )
Niko Ma
2026-05-09 07:07:22 +08:00
190b15c8fe
[AMD] Register 8 CPU-bound unit tests for AMD 1-GPU PR CI (#24569 )
Michael
2026-05-09 07:01:58 +08:00
5fbec0e445
ci: prune per-commit CUDA tests — move 25 files + 13 testcases to test/manual/ (#24721 )
Alison Shao
2026-05-08 15:53:23 -07:00
aefd8e257f
Re-land #23109 : rebase-required mode + fix for grep-no-match abort (#24180 )
Alison Shao
2026-05-08 15:28:57 -07:00
fa8985486e
[test/fix]: isolate VLM MMMU eval output dirs to fix nightly-4-gpu cross-test pollution (#24623 )
Jimmy Shong and gemini-code-assist[bot]
2026-05-08 17:01:53 -05:00
5dc4c7bef1
Add speculative decoding naming convention rule (#24094 )
Liangsheng Yin
2026-05-08 14:52:31 -07:00
096ad02b06
[Model] Laguna-XS.2 Model Support (#24204 )
Jimmy Shong
2026-05-08 16:43:13 -05:00
7b707c9222
disable the combination of --enable-two-batch-overlap and --enforce-s… (#24720 )
Cheng Wan
2026-05-08 14:27:35 -07:00
09912fd89d
Remove unnecessary bf16 assert in rotate_activation (#24686 )
Yuhao Yang
2026-05-09 05:00:52 +08:00
f30d1d0b0a
logits: remove blocking H2D copy (#24627 )
Yilong Zhao
2026-05-08 13:22:13 -07:00
672f778512
[NemotronH] Fix expert scale weight loading (#24434 )
Ethan Feng
2026-05-09 03:37:06 +08:00
2cf1a4ab38
feat: Add KV events for Mamba radix cache (#23678 )
zhongdaor-nv and zhongdaor-nv
2026-05-08 11:53:36 -07:00
ca7a8cc61d
[Bugfix] Fix a bug causing NVFP4 to be tested on all gpus like SM90 devices. (#24604 )
Xu Zou and xz-keg
2026-05-09 02:51:30 +08:00
e40e339c72
Filter non-int token ids in benchmark and observe decode-side bootstrap/alloc metrics (#24684 )
Lianmin Zheng
2026-05-08 11:45:37 -07:00
73b8eda103
[diffusion] fix: fix FA3 varlen out argument handling (#24688 )
Mick
2026-05-08 19:01:49 +08:00
17888fa92a
[diffusion] doc: update ltx2 multi-gpu deployment guide (#24682 )
Mick
2026-05-08 18:38:05 +08:00
7f8e7a9130
fix(aiter): drop FP8 KV upcast; use native FP8 path in paged_attentio… (#24129 )
fanxingran and fanxingran
2026-05-08 17:47:48 +08:00
f21d4868dc
[AMD] Replace naive triton RMSNorm with aiter RMSNorm for diffusion model (#24360 )
jacky.cheng
2026-05-08 17:44:13 +08:00
e1150f66db
[AMD][diffusion] Temporal-unfolded batched Conv2D for ROCm VAE decode (#22971 )
YC Yen-Ching Tseng
2026-05-08 17:32:14 +08:00
d32e283947
[NPU] [DOC] refresh npu supported model list (#24676 )
amote-i
2026-05-08 17:08:15 +08:00
80d0226b68
Turn on JIT custom AR implementation by default (#24363 )
Brayden Zhong and b8zhong
2026-05-08 05:05:31 -04:00
73792629d4
[AMD] Intro SGLANG_DIFFUSION_AITER_FP8_ATTN (#24677 )
HAI
2026-05-08 01:31:00 -07:00
76a1f169b3
[AMD] Add AMD FP8 MLA attention test for Wan2.2-T2V-A14B (#23955 )
jacky.cheng
2026-05-08 16:03:51 +08:00
b22d3cd606
[AMD] Support fp8 MLA for diffusion model (#20319 )
jacky.cheng
2026-05-08 15:56:24 +08:00
19afe73e03
[AMD] Cherry-pick aiter commit for mhc_pre fix (#24665 )
Thomas Wang
2026-05-08 14:49:39 +08:00
55d8223c2b
[sgl-kernel/cpu] support w8a8 int8 model for arm cpu (#16045 )
Yibo Cai
2026-05-08 14:47:06 +08:00
47e9ec11ad
[NPU] [DOC] fix ascend_npu_support_new_models TOC (#24658 )
amote-i
2026-05-08 14:07:00 +08:00
e1bc001872
fix(mimo_v2): auto-disable multimodal when vision/audio configs are absent (#24652 )
JoyFuture
2026-05-08 13:40:08 +08:00
7deed98e1b
[fix] /pause_generation and /continue_generation wrong for --tokenizer-worker-num > 1 (#24462 )
maocheng23 and lawrence-harmonic
2026-05-07 21:32:21 -07:00
2afb450501
[diffusion] optimize: optimize frame returns path (#24616 )
Mick
2026-05-08 12:10:09 +08:00
cdf5771f91
[MUSA][17/N] ci: Add MUSA diffusion, sgl-kernel tests, and CI workflow support (#20672 )
2026-05-08 11:45:21 +08:00
15e6572f21
[MUSA][18/N] Add MUSA-optimized kernel implementations for hot ops (#23255 )
Joey and R0CKSTAR
2026-05-08 11:38:33 +08:00
461bc8af49
[NPU][Doc] Update GLM-5 docs, enabling deepep by default (#23708 )
cen121212
2026-05-08 11:12:35 +08:00
5fa3bb2eaf
Enable flashinfer::trtllm_allreduce_fusion with PDL (#23765 )
2026-05-07 22:41:10 -04:00
d9dddd4d7d
[SPEC V2][2/N] feat: adaptive spec support spec v2 (#23336 )
shuwenn and Qiaolin-Yu
2026-05-08 09:33:47 +08:00
35870d55ac
Deepseek V4 (#23882 )
+6
2026-05-07 18:32:21 -07:00
55224fff08
Add Arm64 CPU Phase 1A CI bootstrap (#22123 )
Mandepudi Rani Chowdary and Ma Mingfei
2026-05-07 20:28:23 -05:00
3c3f0bd55e
Cache empty MatchResult in RadixCache (#24470 )
Lianmin Zheng
2026-05-07 17:13:20 -07:00
c4bb3ce273
Fix stuck when enabling MTP on DSA models (#24635 )
Baizhou Zhang
2026-05-07 17:06:28 -07:00
95fb722dd2
Add registry for custom speculative algorithms (#23991 )
Liangsheng Yin
2026-05-07 16:11:45 -07:00
c2c57068da
fix(http): apply SGLANG_TIMEOUT_KEEP_ALIVE in common.py (#24323 )
Revanth Reddy Airre
2026-05-07 16:01:41 -07:00
5b589ed2e7
feat(constrained): two-phase reasoning grammar + --enable-strict-thinking (#23953 )
Xinyuan Tong
2026-05-07 22:21:51 +01:00
af2a2ac618
fix(function_call): handle Kimi-K2.5 bare numeric tool call IDs (#23950 )
Xinyuan Tong
2026-05-07 22:20:02 +01:00
d8f9d32a05
feat(reasoning): auto-detect reasoning/tool-call parser from chat template (#23952 )
Xinyuan Tong
2026-05-07 22:19:16 +01:00
d2c1034163
[Gemma 4] Adding MTP support (#24436 )
Khoa Pham and Pengyu Chen
2026-05-07 14:08:41 -07:00
f1395af543
fix(openai): map reasoning.enabled to thinking AND enable_thinking (#23951 )
Xinyuan Tong
2026-05-07 22:01:35 +01:00
9cffa5ed6f
[MUSA] Bump torchada to 0.1.54 (#24592 )
R0CKSTAR
2026-05-08 02:45:49 +08:00
be088f8076
fix(router): configure HTTP client connection settings (#24330 )
Revanth Reddy Airre
2026-05-07 11:42:45 -07:00
90a618e37b
[NPU][diffusion] add selectable parallel VAE decode strategies (#23248 )
2026-05-08 02:37:03 +08:00
80a6014243
✨ [diffusion][npu][quant] Add MXFP8 quantization support for Wan2.2 Diffusion on Ascend NPU (#20922 )
2026-05-08 02:30:56 +08:00
7d397ad23d
[NPU]Support model Trinity-mini for Npu, accuracy 90% (#18172 )
McZyWu and sglang-npu-bot
2026-05-08 01:58:18 +08:00
b0225a69dc
[diffusion] optimize: precompute LTX2 guidance perturbation states (#24494 )
Mick
2026-05-08 01:18:42 +08:00
c18879054f
[AMD] Route PR multimodal tests to MI325 (#24614 )
YC Yen-Ching Tseng and bingxche
2026-05-07 23:26:05 +08:00
9c41b1058f
[diffusion] refactor: refactor cfg parallelism framework to support multi-branch CFG for LTX2 (#23736 )
ykcai-daniel and Mick
2026-05-07 07:56:55 -07:00
263cb3b222
[LoRA] Torch Native enhancement: embedding and graph optimization (#21885 )
Vladimir Serov and ronnie_zheng
2026-05-07 17:28:38 +03:00
811d138c8a
Nixl async transfer (#23967 )
ovidiusm
2026-05-07 16:05:43 +02:00
ec4560304b
[Bug Fix] Preserve decode state across retract-resume of GLM-5.1 (#23346 )
Yuxuan Zhang and Shangming Cai
2026-05-07 15:37:53 +02:00
e264b5785d
[PD] Centralize per-room cleanup in common backend (#24601 )
Shangming Cai
2026-05-07 18:47:55 +08:00
3b2c730320
[AMD] Enable dual-stream MoE on ROCm (#24005 )
inkcherry
2026-05-07 17:27:24 +08:00
92f281f856
[Spec][trtllm] use decode kernel for draft extend (#24566 )
Hanming Lu
2026-05-07 02:25:26 -07:00
a6dc49545e
Let bypass-fastfail label skip stage-to-stage wait (#24598 )
Liangsheng Yin
2026-05-07 02:20:27 -07:00
684638e053
Fix prefill batch iter logging under overlap (#20845 )
weireweire
2026-05-07 17:10:42 +08:00
9dfb1d2ebe
[Intel GPU] Fix flash_mla_get_workspace_size call in intel_xpu (#24372 )
Polisetty V R K Jyothendra Varma
2026-05-07 11:15:32 +05:30
a2586f1c53
[CI] pin NeMo-Skills install to known-good SHA in accuracy_test_runner (#24581 )
Kangyan-Zhou and Claude Opus 4.7
2026-05-06 22:24:48 -07:00
f0368a6666
[LoRA] Use deterministic lora_id for --lora-paths so multi-node ranks agree (#24555 )
Yanbin Jiang and gh1595
2026-05-06 22:20:15 -07:00
d363315de9
fix(router): make HTTP pool idle timeout configurable (#24329 )
Revanth Reddy Airre
2026-05-06 22:11:11 -07:00
8bb0ce192b
Add bypass-fastfail label for check-stage-health (#24577 )
Liangsheng Yin
2026-05-06 21:34:06 -07:00
9ba4aac47b
Fix weight_checker e2e OOM on 32GB GPU + move to nightly (#24559 )
fzyzcjy
2026-05-07 12:06:04 +08:00
65ce9965ce
[Bug Fix] Fix RunAI streamer: corrupted weights, missing quant init, and broken URIs for multimodal models (#22715 )
Jun Liu and Alex Nails
2026-05-07 11:20:04 +09:00
ecb786c8d7
[Kernel] Deprecate DeepGemm in sgl kernel and apply custom wheel sgl-deep-gemm (#24268 )
Baizhou Zhang
2026-05-06 18:59:01 -07:00
eaf074d50e
propagate pytest exit code from test __main__ entries (#24487 )
Liangsheng Yin
2026-05-06 18:46:52 -07:00
4a279d9c36
[R3] Avoid implicit CUDA sync in routed experts DP slicing (#24550 )
Yuzhen Zhou and Byron Hsu
2026-05-06 18:37:36 -07:00
27445f9836
Add ChatCompletionRequest-style support to /v1/tokenize (#23981 )
huangtingwei
2026-05-07 09:35:20 +08:00
3fe8bc987e
Support Triton MLA FP8 KV cache (#20479 )
Brayden Zhong and b8zhong
2026-05-06 21:32:39 -04:00
2e642ea187
[diffusion] chore: align LTX-2 with official (#24313 )
Mick
2026-05-07 08:46:28 +08:00
7fa48916f5
Expand support matrix for pypi wheel release (#24565 )
Baizhou Zhang
2026-05-06 17:39:02 -07:00