kvcache-ai/sglang
1
0
Fork 0
mirror of https://github.com/kvcache-ai/sglang.git synced 2026-07-02 21:37:11 +00:00
Code Issues Packages Projects Releases Wiki Activity
12,361 Commits 157 Branches 0 Tags
80a601424325f7ea5320ef35c620d06009f76cf2
Commit Graph

8205 Commits

Author SHA1 Message Date
Junlin Wu
80a6014243 ✨ [diffusion][npu][quant] Add MXFP8 quantization support for Wan2.2 Diffusion on Ascend NPU (#20922) 
Co-authored-by: ronnie_zheng <zl19940307@163.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2026-05-07 21:30:56 +03:00
McZyWu
7d397ad23d [NPU]Support model Trinity-mini for Npu, accuracy 90% (#18172) 
Co-authored-by: sglang-npu-bot <sglangnpu@163.com>
 2026-05-07 20:58:18 +03:00
Mick
b0225a69dc [diffusion] optimize: precompute LTX2 guidance perturbation states (#24494) 2026-05-08 01:18:42 +08:00
ykcai-daniel
9c41b1058f [diffusion] refactor: refactor cfg parallelism framework to support multi-branch CFG for LTX2 (#23736) 
Co-authored-by: Mick <mickjagger19@icloud.com>
 2026-05-07 22:56:55 +08:00
Vladimir Serov
263cb3b222 [LoRA] Torch Native enhancement: embedding and graph optimization (#21885) 
Co-authored-by: ronnie_zheng <zl19940307@163.com>
 2026-05-07 17:28:38 +03:00
ovidiusm
811d138c8a Nixl async transfer (#23967) 
Signed-off-by: Ovidiu Mara <ovidium@nvidia.com>
 2026-05-07 22:05:43 +08:00
Yuxuan Zhang
ec4560304b [Bug Fix] Preserve decode state across retract-resume of GLM-5.1 (#23346) 
Co-authored-by: Shangming Cai <csmthu@gmail.com>
 2026-05-07 21:37:53 +08:00
Shangming Cai
e264b5785d [PD] Centralize per-room cleanup in common backend (#24601) 
Signed-off-by: Shangming Cai <csmthu@gmail.com>
 2026-05-07 18:47:55 +08:00
inkcherry
3b2c730320 [AMD] Enable dual-stream MoE on ROCm (#24005) 
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
 2026-05-07 02:27:24 -07:00
Hanming Lu
92f281f856 [Spec][trtllm] use decode kernel for draft extend (#24566) 2026-05-07 02:25:26 -07:00
weireweire
684638e053 Fix prefill batch iter logging under overlap (#20845) 2026-05-07 02:10:42 -07:00
Polisetty V R K Jyothendra Varma
9dfb1d2ebe [Intel GPU] Fix flash_mla_get_workspace_size call in intel_xpu (#24372) 
Signed-off-by: P V R K Jyothendra Varma <polisetty.v.r.k.jyothendra.varma@intel.com>
 2026-05-07 13:45:32 +08:00
Kangyan-Zhou
a2586f1c53 [CI] pin NeMo-Skills install to known-good SHA in accuracy_test_runner (#24581) 
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-06 22:24:48 -07:00
Yanbin Jiang
f0368a6666 [LoRA] Use deterministic lora_id for --lora-paths so multi-node ranks agree (#24555) 
Co-authored-by: gh1595 <278903827+gh1595@users.noreply.github.com>
 2026-05-06 22:20:15 -07:00
Jun Liu
65ce9965ce [Bug Fix] Fix RunAI streamer: corrupted weights, missing quant init, and broken URIs for multimodal models (#22715) 
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
 2026-05-06 19:20:04 -07:00
Baizhou Zhang
ecb786c8d7 [Kernel] Deprecate DeepGemm in sgl kernel and apply custom wheel sgl-deep-gemm (#24268) 2026-05-06 18:59:01 -07:00
Liangsheng Yin
eaf074d50e propagate pytest exit code from test __main__ entries (#24487) 2026-05-06 18:46:52 -07:00
Yuzhen Zhou
4a279d9c36 [R3] Avoid implicit CUDA sync in routed experts DP slicing (#24550) 
Co-authored-by: Byron Hsu <byronhsu1230@gmail.com>
 2026-05-06 18:37:36 -07:00
huangtingwei
27445f9836 Add ChatCompletionRequest-style support to /v1/tokenize (#23981) 2026-05-06 18:35:20 -07:00
Brayden Zhong
3fe8bc987e Support Triton MLA FP8 KV cache (#20479) 
Co-authored-by: b8zhong <b8zhong@users.noreply.github.com>
 2026-05-06 18:32:39 -07:00
Mick
2e642ea187 [diffusion] chore: align LTX-2 with official (#24313) 2026-05-07 08:46:28 +08:00
Xiaoyu Zhang
a9a8b20a90 [codex] Optimize Z-Image packed QKV (#24117) 2026-05-07 07:51:22 +08:00
gh1595
ece7e95b65 [LoRA] Fix qkv_proj LoRA buffer sizing when tp_size > num_key_value_heads (#24420) 
Co-authored-by: Yanbin Jiang <jybsuper@gmail.com>
 2026-05-06 14:51:30 -07:00
Lianmin Zheng
b859f7ffba Improve metrics, observability, and PD deploy tooling (#24521) 2026-05-06 11:27:35 -07:00
Xiaoyu Zhang
d86f2916cc Fix diffusion fallback guards and validation (#23335) 2026-05-07 00:05:43 +08:00
Shangming Cai
32d9998b9d [PD] Prevent update_status to Failed from cleared entries (#24539) 
Signed-off-by: Shangming Cai <csmthu@gmail.com>
 2026-05-06 23:32:04 +08:00
sky
bfc1aeae13 [CP] Register KV cache allgather buffer with symmetric memory (#24040) 
Signed-off-by: wangfakang <fakangwang@gmail.com>
 2026-05-06 23:24:36 +08:00
fzyzcjy
c4c5541618 Support getting checksums in weight checker (#24537) 2026-05-06 22:59:28 +08:00
fzyzcjy
ae5ae840f6 Refactor buffer patterns in weight checker (#24538) 2026-05-06 22:52:07 +08:00
Ke Bao
eb5f0fbeef Support swa HiCache for unified radix cache (#23391) 
Co-authored-by: hzh0425 <hzh0425@apache.org>
 2026-05-06 22:19:25 +08:00
fzyzcjy
491051c622 Cherry pick weight_checker _weight_fp32 buffer skip from #22663 (#24534) 
Co-authored-by: JD <jaedon.guo@gmail.com>
 2026-05-06 21:21:12 +08:00
fzyzcjy
0d40931b08 Cherry pick weight_checker non-persistent buffer pattern list from #21278 (#24533) 
Co-authored-by: JD <jaedon.guo@gmail.com>
 2026-05-06 21:14:01 +08:00
fzyzcjy
864f9633f2 Cherry pick weight_checker fp8 dequant fix and non-persistent buffer skip from #21494 (#24532) 
Co-authored-by: Yueming Yuan <yym022502@gmail.com>
 2026-05-06 21:13:17 +08:00
Lianmin Zheng
d4d4b04d66 [PD] Fix missing update_status call in abort() across all KV backends (#24522) 2026-05-06 05:30:11 -07:00
cctry
163bf1ba71 [PD] Fix KV transfer metrics (#24416) 
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
 2026-05-06 03:44:48 -07:00
Xiaoyu Zhang
b67df7cd1b [Codex] Diffusion handle non-contiguous CFG communication (#24332) 
Co-authored-by: BBuf Codex <bbuf-codex@users.noreply.github.com>
 2026-05-06 17:27:14 +08:00
sky
c8bc23522f Refactor: decouple segment tracking from comm registration (#21392) 
Signed-off-by: wangfakang <fakangwang@gmail.com>
 2026-05-06 17:07:58 +08:00
fzyzcjy
a858fda708 Add e2e test with log snapshot in dumper grafter (#24513) 2026-05-06 17:00:13 +08:00
fzyzcjy
8527db0a91 Enhance diff and tensor-info logging in dumper grafter (#24512) 2026-05-06 16:58:08 +08:00
fzyzcjy
75943cfbcf Support per-call extras and dataclass transform input in dumper grafter (#24511) 2026-05-06 16:57:44 +08:00
fzyzcjy
833279eb2e Support multi-rank exchange via all_gather_object in dumper grafter (#24510) 2026-05-06 16:57:20 +08:00
fzyzcjy
ebd64f5d40 Support user-supplied recv-side transform in dumper grafter (#24509) 2026-05-06 16:56:52 +08:00
fzyzcjy
9a65f0ac26 Support t2b direction and overlap protection in dumper grafter (#24508) 2026-05-06 16:56:24 +08:00
fzyzcjy
58487e68e5 Support cross-system tensor grafting in dumper (#24507) 2026-05-06 16:55:40 +08:00
fzyzcjy
61104d7d0a Add prefixed _log helper in dumper (#24506) 2026-05-06 16:54:20 +08:00
Mick
fbebfdec9a [diffusion] fix: fix diffusion FSDP sharding (#24431) 2026-05-06 14:55:51 +08:00
cctry
660a77f221 Silence noisy health-check race log in TokenizerManager (#24466) 2026-05-05 21:06:43 -07:00
ybyang
3da87902d7 [HiSparse] Support FP8 KV cache by routing to flashmla_kv backend (#23013) 
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
Co-authored-by: Kangyan-Zhou <zky314343421@gmail.com>
 2026-05-06 03:18:30 +00:00
Night
b2420d72ff [RL] DeepEP support for --enable-return-routed-experts (#16859) 
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
Co-authored-by: Junrong Lin <33685709+ocss884@users.noreply.github.com>
 2026-05-05 20:01:07 -07:00
Xiaoyu Zhang
d7385b575f [Diffusion] Optimize Hunyuan3D shape denoising (#24287) 2026-05-06 10:10:09 +08:00