Commit Graph

3275 Commits

Author SHA1 Message Date
Lianmin Zheng
c2b7ddca49 [Minor] cleanup unused imports (#6358) 2025-05-16 14:52:38 -07:00
Lianmin Zheng
abebd9399c Update CODEOWNERS (#6359) 2025-05-16 14:51:36 -07:00
Fr4nk1in
4bd2952a37 feat: add dp attention support for Qwen 2/3 MoE models, fixes #6088 (#6121)
Co-authored-by: King.Zevin <zevin@mail.ustc.edu.cn>
Co-authored-by: Yi Zhang <1109276519@qq.com>
2025-05-16 14:44:10 -07:00
Elfie Guo
6fc9357503 [2/2] Add python wrapper for CUTLASS FP8 Blockscale MoE Kernel. (#5694) 2025-05-16 13:14:07 -07:00
Baizhou Zhang
839fb31e5f [Fix] Improve dependencies for Blackwell image (#6334) 2025-05-16 12:38:22 -07:00
Yury Sulsky
f19a9204cd Support precomputed multimodal features for Qwen-VL and Gemma3 models. (#6136)
Co-authored-by: Yury Sulsky <ysulsky@tesla.com>
2025-05-16 12:26:15 -07:00
Elfie Guo
c23a7072b6 Upgrade CUTLASS 4.0 (#6336)
Co-authored-by: zhyncs <me@zhyncs.com>
2025-05-15 17:42:23 -07:00
Lianmin Zheng
e07a6977e7 Minor improvements of TokenizerManager / health check (#6327) 2025-05-15 15:29:25 -07:00
Qiaolin Yu
cd8d4b9dfc Fix lora bench (#6302) 2025-05-15 10:09:55 -07:00
fzyzcjy
f194e14fb7 Reduce MoE memory usage (#6147) 2025-05-15 09:38:28 -07:00
Yi Liu
cfc9f9ab8d Fix gpu mem check on CPU (#6317)
Signed-off-by: yiliu30 <yi4.liu@intel.com>
2025-05-15 09:37:45 -07:00
Chunyuan WU
fb4959b2c5 Add fp8 gemm kernel for CPU in sgl-kernel and add gemm UT (#6216)
Co-authored-by: YanbingJiang <yanbing.jiang@intel.com>
Co-authored-by: mingfeima <mingfei.ma@intel.com>
2025-05-15 09:10:40 -07:00
JieXin Liang
9a405274e2 [misc] remove redundant platform codes (#6298) 2025-05-15 00:51:30 -07:00
quinnrong94
2e4babdb0a [Feat] Support FlashMLA backend with MTP and FP8 KV cache (#6109)
Co-authored-by: Yingyi <yingyihuang2000@outlook.com>
Co-authored-by: neiltian <neiltian@tencent.com>
Co-authored-by: lukec <118525388+sleepcoo@users.noreply.github.com>
Co-authored-by: kexueyu <kexueyu@tencent.com>
Co-authored-by: vincentmeng <vincentmeng@tencent.com>
Co-authored-by: pengmeng <pengmeng@tencent.com>
2025-05-15 00:48:09 -07:00
Zilin Zhu
44a3783d13 [fix][RL] Remove the incorrect barrier in init_weights_update_group (#5914) 2025-05-14 19:15:21 -07:00
Junrong Lin
f3bf611054 feat: add flush cache to EngineBase and HttpServerEngineAdapter (#6009) 2025-05-14 19:15:02 -07:00
Hubert Lu
198b9056d1 [AMD] Fix Llama 4 Scout and Maverick accuracy issues on MI300X (#6274) 2025-05-14 22:07:29 +00:00
Sai Enduri
73eb67c087 Enable unit tests for AMD CI. (#6283) 2025-05-14 12:55:36 -07:00
Brayden Zhong
9a91fa0ed1 docs: fix a bad redirect (#6300) 2025-05-14 10:27:19 -07:00
Mick
cd7c8a8de6 doc: update developer guide regarding mllms (#6138)
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: XinyuanTong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
2025-05-14 23:13:13 +08:00
Lifu Huang
3e350a931e [Bug] Fix accidental logger override caused by internVL. (#6282) 2025-05-13 23:29:25 -07:00
Ying Sheng
fb71725c98 Fix a bug in schedule_policy (#6276) 2025-05-13 18:04:00 -07:00
Chang Su
912788c095 perf: optimize local_block_table memory allocation (#6273) 2025-05-13 17:18:38 -07:00
blzheng
0f75b907c6 [CPU] Add CMakeLists.txt for sgl-kernel (#6115) 2025-05-13 15:30:37 -07:00
Yineng Zhang
16267d4fa7 chore: bump v0.4.6.post4 (#6245) 2025-05-13 01:57:51 -07:00
Sai Enduri
0f5cb8cae1 Enable MI325X AMD CI. (#6259) 2025-05-13 01:49:33 -07:00
JieXin Liang
17299f088a [misc] deep_gemm fallback to NVRTC when NVCC not found (#6252) 2025-05-13 01:41:35 -07:00
Kiv Chen
5380cd7ea3 model(vlm): pixtral (#5084) 2025-05-13 00:16:10 -07:00
Cheng Wan
b2e95f62b4 Fix two issues related to --moe-dense-tp-size=1 (#5657)
Co-authored-by: liusy58 <liusy58@linux.alibaba.com>
Co-authored-by: 颉沆 <xiehang.lsy@alibaba-inc.com>
2025-05-12 23:51:39 -07:00
Stefan He
1ab14c4c5c [VERL Use Case] Add torch_memory_saver into deps (#6247) 2025-05-12 19:09:03 -07:00
Brayden Zhong
3c32895cbe [Llama4] Add docs note about enable multimodal (#6235) 2025-05-13 10:05:47 +08:00
Lianmin Zheng
ac2324c177 Skip the flaky test_stateful_custom_logit_processor (#6251) 2025-05-12 18:29:41 -07:00
fzyzcjy
ef8ec07b2c Support tuning moe for llama 4 model (#6042) 2025-05-12 15:47:01 -07:00
Yineng Zhang
f24fc5b86d fix typo (#6248) 2025-05-12 15:45:12 -07:00
Lianmin Zheng
d18c6b3358 Support incremental streaming of logprob/token_ids between scheduler and detokenizer (#6225)
Co-authored-by: SangBin Cho <rkooo567@gmail.com>
2025-05-12 14:33:38 -07:00
shangmingc
f1c896007a [PD] Add support for different TP sizes per DP rank (#5922)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-05-12 13:55:42 -07:00
Sai Enduri
983c663de6 Update AMD nightly deps. (#6241) 2025-05-12 13:39:20 -07:00
Yineng Zhang
f94543d22b chore: add hf_xet dep (#6243) 2025-05-12 13:08:40 -07:00
Lianmin Zheng
e8e18dcdcc Revert "fix some typos" (#6244) 2025-05-12 12:53:26 -07:00
Ying Sheng
bad7c26fdc [PP] Fix init_memory_pool desync & add PP for mixtral (#6223) 2025-05-12 12:38:09 -07:00
Brayden Zhong
12319a6787 [Docs] Add docs for SGLANG_ and SGL_ environment variables (#6206) 2025-05-13 01:45:41 +08:00
applesaucethebun
d738ab52f8 fix some typos (#6209)
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
2025-05-13 01:42:38 +08:00
shangmingc
3ee40ff919 [CI] Re-enable pd disaggregation test (#6231)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-05-12 10:09:12 -07:00
shangmingc
0f334945c6 [CI] Fix PD mooncake dependency error (#6212)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-05-12 10:08:49 -07:00
Lianmin Zheng
fba8eccd7e Log if cuda graph is used & extend cuda graph capture to cuda-graph-max-bs (#6201)
Co-authored-by: SangBin Cho <rkooo567@gmail.com>
2025-05-12 00:17:33 -07:00
Sai Enduri
7d3a3d4510 Update AMD CI docker to v0.4.6.post3-rocm630. (#6213) 2025-05-12 00:00:46 -07:00
Cheng Wan
25c83fff6a Performing Vocabulary Parallelism for LM Head across Attention TP Groups (#5558)
Co-authored-by: liusy58 <liusy58@linux.alibaba.com>
2025-05-11 23:36:29 -07:00
Xiaoyu Zhang
9f2c9568f0 [doc] add a note for --n-share-experts-fusion args (#6154) 2025-05-11 23:18:38 -07:00
fzyzcjy
3f2702ae51 Fix start_profile does not support with_stack and record_shapes (#6043) 2025-05-11 23:11:32 -07:00
Lianmin Zheng
6ea05950b1 Fix release-docs.yml to not use python 3.9 (#6204) 2025-05-11 16:04:55 -07:00