kvcache-ai/sglang
1
0
Fork 0
mirror of https://github.com/kvcache-ai/sglang.git synced 2026-07-12 18:36:58 +00:00
Code Issues Packages Projects Releases Wiki Activity
11,824 Commits 157 Branches 0 Tags
cfd49e233ceb94de3f702f70aef06e299836aede
Commit Graph

1518 Commits

Author SHA1 Message Date
blzheng
0dcfae5553 [CPU] Add gemma4_rmsnorm_cpu kernel (#22842) 
Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
 2026-04-17 13:03:16 +08:00
Chunyuan WU
6c89214584 [CPU][sgl-kernel] extend_attention_cpu and flash_attn_varlen_func: fix nan for large seq (#22434) 
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
 2026-04-17 13:01:01 +08:00
Baizhou Zhang
3c46ff2ac5 fix: restore CPU flash_attn test to use sgl_kernel directly (#22573) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-10 21:39:20 -07:00
jianan-gu
2ab141547d [CPU] Add apply_routed_scaling_factor_on_output support for biased_grouped_topk fusion (#22413) 
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
 2026-04-10 15:16:05 +08:00
Sundara Raman Ramachandran
a64905a7b8 [CICD] [prefill-only] Consolidate prefill-only model E2E tests (#22405) 2026-04-09 00:54:34 -07:00
Sundara Raman Ramachandran
712c8c5051 [Score API] Add SequenceClassification Model support (#22118) 2026-04-08 01:30:58 -07:00
Rain Jiang
1a8eb890f6 Kernels community fa3 (#20796) 2026-04-07 12:48:44 -07:00
Huaiyu, Zheng
68f4c52d34 fix ut test_moe (#21735) 2026-04-03 21:57:11 -07:00
Baizhou Zhang
29d8e959d7 [CI] Remove stale Ascend suite entries from test/srt/run_suite.py (#21978) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-02 16:47:19 -07:00
Cherry_ming
e67b95d66b [NPU]Add a full test pipeline on NPU, resolve issues in the NPU test architecture (#20751) 2026-04-01 19:56:31 +08:00
blzheng
ed01e1d5d6 [CPU] add kernel apply_rotary_pos_emb_cpu for Qwen3-VL and Qwen3-Omni (#13121) 
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
 2026-03-29 23:43:46 -07:00
Lianmin Zheng
27ac831a84 docs: improve CI and testing documentation (#21202) 
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-23 10:48:50 -07:00
Cao E
274581fb77 Add support for more batch sizes in cpu_graph_runner (#13881) 2026-03-19 09:50:56 -07:00
blzheng
cd22aa27a9 [CPU] Add FP8 Bmm support (#9744) 
Co-authored-by: Fan Yin <1106310035@qq.com>
 2026-03-18 22:19:48 -07:00
blzheng
c2b01bd2fc [CPU] fix bug in AVX512 implementation of flash_attn_softmax (#20220) 
Co-authored-by: Wu, Chunyuan <chunyuan.wu@intel.com>
 2026-03-18 22:18:47 -07:00
Zaili Wang
2f4babe32b [CPU] support LayerNorm with 3D shape (#15075) 
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
 2026-03-18 22:15:24 -07:00
blzheng
dc6aa26ce9 [CPU] Add mrope kernel for Qwen3-vl (#12531) 
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
 2026-03-18 22:12:48 -07:00
Juan Muneton
4052b53227 fix scheduler for non-cuda devices and disable piecewise cuda graph f… (#19992) 
Co-authored-by: Kangyan-Zhou <zky314343421@gmail.com>
 2026-03-18 21:54:19 -07:00
Juan Muneton
7458407437 Fix InternVL and vision attention for non-CUDA backends (e.g. XPU) (#19997) 
Co-authored-by: Yang Wang <mr.yang.wang@outlook.com>
 2026-03-14 23:24:41 -07:00
SoluMilken
c95dc88f86 [CI] migrate ascend-gptq from test/srt to test/registered (#19628) 2026-03-14 00:28:57 -07:00
wenxuewuhd
11b76d24dc [NPU] [DLLM]DLLM LLaDA2.x graph mode support with NPU speedup modifications (#18485) 
Co-authored-by: Zhang-Xiaoxue <xiaoxuezhang17@outlook.com>
Co-authored-by: dawncc <dawn.cc022@gmail.com>
Co-authored-by: lixinqi7 <li_xinqi7@163.com>
Co-authored-by: rangejay <rangejay1st@163.com>
 2026-03-09 22:41:05 +08:00
YeChang Guo
13bdc7bf4a [Feature][NPU]: add runtime support for AutoRound quantized models (#16699) 
Co-authored-by: root <root@localhost.localdomain>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
 2026-03-07 18:03:55 +03:00
YeChang Guo
6910c1b281 [Feature][NPU]: add runtime support for GPTQ-quantized MoE models (#16364) 
Co-authored-by: GuoYechang <52730608+GuoYechang@users.noreply.github.com>
Co-authored-by: root <root@localhost.localdomain>
 2026-03-04 16:02:19 +03:00
Alison Shao
eb6bcc5c86 [CI] Register test_quant_config_parsing.py in CI suite (#19809) 
Co-authored-by: Alison Shao <alisonshao@Mac.attlocal.net>
 2026-03-03 16:53:31 -08:00
Praneth Paruchuri
f7897def96 [Feature] Improve weight loading log (#18651) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-03-03 14:16:13 -08:00
Yuwei An
c64274c746 Piecewise Cuda Graph set default (#16331) 2026-03-02 23:18:07 +08:00
Cherry_ming
1eb40d8d45 [NPU]Optimize the PR pipeline to reduce E2E runtime (#18767) 
Co-authored-by: Sugar920 <121632458+Sugar920@users.noreply.github.com>
 2026-02-28 17:06:03 +08:00
Baizhou Zhang
776709efe8 [3/n] deepseek_v2.py Refactor: Migrate MLA forward method in deepseek_v2.py (#19122) 2026-02-27 13:37:29 -08:00
SoluMilken
07a24f1a38 update pre-commit config (#18860) 2026-02-16 00:18:31 +08:00
shuwenn
3299c4f9c1 [CI] feat: add early exit to wait_for_server when process dies (#18602) 2026-02-13 16:46:09 -08:00
aaaandychen
6a4b81e2d9 Refactor(qwen3-vl) optimize position encoding interpolation (#16781) 
Signed-off-by: chenzhenyang <andy271828@163.com>
Signed-off-by: chenzhenyang <chenzhenyang@moonshot.cn>
Co-authored-by: chenzhenyang <chenzhenyang@moonshot.cn>
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
 2026-02-05 10:26:35 -08:00
Meng, Hengyu
368936a62b [XPU] Integrate MoE and minor improvements in XPU attention backend (#13561) 2026-02-04 23:09:59 -08:00
Alison Shao
a0bae4c343 Migrate 4-GPU/8-GPU workflow jobs to stage-c and add CI registry decorators (#17299) 2026-01-31 22:37:22 -08:00
b8zhong
398d13a189 [Perf] Add Flashinfer DeepGEMM SM90 for SwapAB Optimization (#15514) 
Co-authored-by: Brayden Zhong <b8zhong@users.noreply.github.com>
 2026-02-01 08:56:23 +08:00
jianan-gu
c35aa0238c [CPU][INT4] Add INT4 kernels for CPU (#8226) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-01-29 22:30:13 -08:00
Ma Mingfei
88f7759402 [CPU] optimize flash_attn_varlen_func (#15708) 2026-01-29 22:07:05 -08:00
22dimensions
7b79326751 [NPU] support GPTQ quantization on npu (#15203) 
Signed-off-by: 22dimensions <waitingwind@foxmail.com>
 2026-01-29 15:48:18 +08:00
kk
f1384f5293 Integration mori backend for EP a2a data communication (#17012) 
Co-authored-by: Duyi-Wang <duyi.wang@amd.com>
Co-authored-by: billishyahao <bill.he@amd.com>
Co-authored-by: HaiShaw <hixiao@gmail.com>
 2026-01-28 19:07:34 -08:00
Even Zhou
6077de1237 [CI] [NPU] npu ci use existing modelscope model (#17868) 2026-01-28 16:51:41 +08:00
Baizhou Zhang
1d942e4eef [DeepSeek] Update tests and document for DeepSeek V3.2 NVFP4 checkpoint (#17657) 2026-01-27 22:10:57 +08:00
Shangming Cai
3ad3268e06 [CI] Skip PD hybrid attention test with different TP temporarily (#17791) 2026-01-27 10:59:33 +08:00
Alison Shao
6c0f9b4824 Add test_gpt_oss_4gpu.py to B200 test suite (#17743) 2026-01-26 21:57:06 +08:00
xjx471258437
9bd92ba0f6 Support PD disaggregation with different TP/DP size for Qwen3-Next (#16056) 
Co-authored-by: xjx392321 <xjx392321@alibaba-inc.com>
 2026-01-25 15:34:02 +08:00
Nicolas Castet
48e9daadff Support symmetric memory pre-allocation to avoid fragmentation (#17089) 2026-01-23 17:57:04 +08:00
Even Zhou
69ac8b58f7 [NPU] [CI] temporarily disable mtp test (#17614) 2026-01-23 15:17:31 +08:00
Alison Shao
d7dd0b8832 Re-enable unit-test-deepep-8-gpu and unit-test-backend-4-gpu-gb200 (#17438) 2026-01-23 14:31:44 +08:00
Alison Shao
9be2a3a9a3 Remove test_gpt_oss_4gpu.py from __not_in_ci__ (keep in per-commit-4-gpu) (#17534) 2026-01-21 15:31:03 -08:00
Alison Shao
85d9af51da Temporarily disable flaky test_gpt_oss_4gpu.py on B200 (#17528) 2026-01-21 14:01:04 -08:00
ympcMark
f7a5e425c3 [3/N] Achieve fault tolerance at the DP level (#11657) 
Co-authored-by: UNIDY <unidy2002@outlook.com>
Co-authored-by: Hank Han <hanhan7630@outlook.com>
 2026-01-20 18:47:08 +08:00
Hudson Xing
c1282da236 fix(ci): apply MMMU retry logic to all affected test files (#17329) 2026-01-19 10:00:29 -08:00