chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity
5,447 Commits 1 Branch 0 Tags
9d7e82a0aba0dda2aee61be2513819f3e7dece46
Commit Graph

297 Commits

Author SHA1 Message Date
Qiaolin Yu
e2ac7888b8 [2/2] Support deterministic inference for temperature > 0 (#10678) 
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: hebiao064 <hebiaobuaa@gmail.com>
 2025-09-21 19:36:08 -07:00
Baizhou Zhang
8ecef73f12 [1/2] Support deterministic inference with flashinfer attention backend (#10645) 
Co-authored-by: hebiao064 <hebiaobuaa@gmail.com>
Co-authored-by: Qiaolin-Yu <liin1211@outlook.com>
 2025-09-19 23:34:29 -07:00
Zhihao Zhang
e7bc600304 [Feature] Speculative decoding support lookahead (#9873) 
Co-authored-by: a4zhangfei <a4zhangfei@qq.com>
Co-authored-by: Qiaolin-Yu <liin1211@outlook.com>
 2025-09-18 16:42:41 -07:00
harrisonlimh
14fdd52740 feat: add priority based scheduling with priority based request acceptance and preemption (#8746) 2025-09-16 17:10:10 -07:00
Shu Wang
3df05f4d6a [NVIDIA] [3/N] Nvfp4 Masked Gemm: Add flashinfer grouped_gemm_nt_masked (#9199) 2025-09-11 20:18:43 -07:00
ryang
dccf52f9c8 [UT for RL] Add UT to cover release/resume memory case for moe model (#8803) 2025-09-09 19:25:12 -07:00
Rain Jiang
7a40e4f4a6 fix the cutlass moe tests (#10182) 2025-09-08 16:24:55 -07:00
Yineng Zhang
b7d1f17b8d Revert "enable auto-round quantization model (#6226)" (#10148) 2025-09-07 22:31:11 -07:00
Weiwei
c8295d2353 enable auto-round quantization model (#6226) 
Signed-off-by: Zhang, Weiwei1 <weiwei1.zhang@intel.com>
 2025-09-07 22:05:35 -07:00
Qiaolin Yu
8cda5a622c Standalone speculative decoding (#10090) 2025-09-07 20:55:09 -07:00
Shangming Cai
00974e4f6e [CI] Refactor disaggregation tests (#10068) 
Signed-off-by: Shangming Cai <csmthu@gmail.com>
 2025-09-06 22:14:46 +08:00
Cheng Wan
3fa62da78c [7/N] MoE Refactor: the implementation of new framework (#9269) 2025-09-05 21:09:09 -07:00
DevashishLal-CB
13705dae06 [Fix] Add speculative_draft_model_revision to server_args (#5255) 
Signed-off-by: Devashish Lal <devashish@rivosinc.com>
 2025-09-05 19:45:46 +08:00
Elfie Guo
bebd0576e5 Integrate trtllm ragged attention for prefill self-attention (#9801) 2025-09-05 17:18:00 +08:00
Liangsheng Yin
6e95f5e5bd Simplify Router arguments passing and build it in docker image (#9964) 2025-09-05 12:13:55 +08:00
Lianmin Zheng
397448ebbc [Auto Sync] Update parallel_state.py, few_shot_gsm8k.py (20250903) (#9986) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Leon Gao <leon.gao19@gmail.com>
 2025-09-03 16:55:43 -07:00
chenxj
d4a938417d [feat] Support tp mode for DeepSeek-R1-W4AFP8 (#8118) 
Co-authored-by: yuhyao <827623970@qq.com>
 2025-09-01 22:17:26 -07:00
Faraz
ff9b561817 Fix TRTLLM MLA Cuda KV Blocks Causing accuracy drop (#9675) 2025-08-29 17:16:10 -07:00
Qi Yuhang
fda4792620 Update CUTLASS 4.2 & Enable K-Major Scale Factor for SM90 FP8 Blockwise Group GEMM (#9559) 2025-08-24 23:24:43 -07:00
DiweiSun
029e0af31d ci: enhance xeon ci (#9395) 2025-08-21 03:35:17 -07:00
Lifu Huang
b0980af89f Support pinning adapter via server args. (#9249) 2025-08-20 16:25:01 -07:00
kousakawang
0fc54b971e [fix]: fix cutlass moe ut and and Opt H20 cutlass groupGemm performance (#9272) 
Co-authored-by: wanghanpei <wanghanpei@bytedance.com>
 2025-08-17 13:09:49 -07:00
Netanel Haber
845d12a979 model: support nvidia/Llama-3_3-Nemotron-Super-49B-v1 (#9067) 
Co-authored-by: Kyle Huang <kylhuang@nvidia.com>
 2025-08-17 01:48:15 -07:00
Hank Han
81da16f6d3 [CI] add deepseek w4a8 test on h20 ci (#7758) 2025-08-16 01:54:13 -07:00
Cheng Wan
295895120d [6/N] MoE Refactor: Cleanup MoE-related configs (#8849) 2025-08-14 21:14:53 -07:00
Hongbo Xu
a669bc2f74 Replace sglang.srt.layers.quantization.scalar_types with sgl_kernel.scalar_type (#8951) 2025-08-13 19:41:41 -07:00
Faraz
f508cd3cb7 TRTLLM-MLA FP8 path (#8638) 
Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>
 2025-08-11 14:02:13 -07:00
Lianmin Zheng
2449a0afe2 Refactor the docs (#9031) 2025-08-10 19:49:45 -07:00
Lianmin Zheng
b58ae7a2a0 Simplify frontend language (#9029) 2025-08-10 10:59:30 -07:00
fzyzcjy
442534aa44 Add CI for gpt-oss model on hopper (#8851) 2025-08-09 00:34:23 -07:00
Trevor Morris
a60f88b5a4 Add unit test for flashinfer fp4 moe (#8330) 
Co-authored-by: Yineng Zhang <me@zhyncs.com>
 2025-08-08 17:55:37 -07:00
Minglei Zhu
6ee6619b7a add zai-org/GLM-4.5-Air-FP8 model into nightly CI (#8894) 2025-08-08 01:44:19 -07:00
Lifu Huang
6210e2c4f0 Support GPU pinning for LoRA (#8697) 2025-08-06 19:39:45 -07:00
Lifu Huang
8675bdf246 Support limiting max loaded loras in CPU. (#8650) 2025-08-03 00:02:23 -07:00
Lianmin Zheng
e314b084c5 [FIX] Fix the nightly CI by disabling swa mem pool for gemma2 (#8693) 2025-08-02 18:43:14 -07:00
Cheng Wan
6c88f6c8d9 [5/N] MoE Refactor: Update MoE parallelism arguments (#8658) 2025-08-01 01:20:03 -07:00
Faraz
4b04998d38 TRTLLM Gen MLA Decode Kernel Integration (same as #7938) (#8632) 
Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>
 2025-07-31 16:03:40 -07:00
harrisonlimh
747dd45077 feat: throttle requests at scheduler based on --max_queued_requests (#7565) 2025-07-28 22:32:33 +08:00
Qiaolin Yu
2810338401 [feat] Support different attention backends for prefill and decode (#6338) 
Co-authored-by: tianqilin.99 <tianqilin.99@bytedance.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
 2025-07-28 11:42:29 +08:00
fzyzcjy
62222bd27e Minor tool for comparison of benchmark results (#7974) 2025-07-27 00:27:50 -07:00
Lifu Huang
5c705b1dce Add perf tests for LoRA (#8314) 2025-07-26 14:55:22 -07:00
Hubert Lu
af4b9bae95 [AMD] Add silu_and_mul, gelu_and_mul, gelu_tanh_and_mul, and gelu_quick kernels for AMD GPUs (#7135) 
Co-authored-by: yiakwy-xpu-ml-framework-team <961186938@qq.com>
Co-authored-by: HAI <hixiao@gmail.com>
 2025-07-24 23:44:28 -07:00
Hubert Lu
e50109f2ed [AMD] Remove vllm's scaled_fp8_quant and moe_sum when SGLANG_USE_AITER=1 (#7484) 2025-07-21 17:33:19 -07:00
Pavel Logachev
877e35d775 Add get_hidden_dim to qwen3.py for correct lora (#7312) 2025-07-19 19:31:16 -07:00
Lifu Huang
4e3defe5a7 Support start up LoRA server without initial adapters (#8019) 2025-07-19 15:38:09 -07:00
Lianmin Zheng
bb0e8a32b5 Clean up server args (#8161) 2025-07-19 11:32:52 -07:00
Cheng Wan
15ad6c9086 [1/N] MoE Refactor: refactor select_experts (#7966) 2025-07-19 00:51:15 -07:00
Hongbo Xu
1f76fc8747 [3/n] chore: decouple AWQ implementation from vLLM dependency (#8113) 
Co-authored-by: AniZpZ <zhuangsen.zp@antgroup.com>
 2025-07-18 11:45:22 -07:00
Hank Han
2117f82def [ci] CI supports use cached models (#7874) 2025-07-14 11:42:21 +00:00
Lifu Huang
e2ed9d049a Refactor dynamic LoRA update to fix incorrect handling of variant weight shapes (#7844) 2025-07-13 18:36:01 -07:00