sglang 0.4.0__py3-none-any.whl → 0.4.0.post1__py3-none-any.whl

{sglang-0.4.0.dist-info → sglang-0.4.0.post1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sglang
-Version: 0.4.0
+Version: 0.4.0.post1
 Summary: SGLang is yet another fast serving framework for large language models and vision language models.
 License:                                  Apache License
                                    Version 2.0, January 2004
@@ -239,7 +239,7 @@ Requires-Dist: xgrammar>=0.1.4; extra == "runtime-common"
 Provides-Extra: srt
 Requires-Dist: sglang[runtime_common]; extra == "srt"
 Requires-Dist: torch; extra == "srt"
-Requires-Dist: vllm>=0.6.3.post1; extra == "srt"
+Requires-Dist: vllm<=0.6.4.post1,>=0.6.3.post1; extra == "srt"
 Requires-Dist: cuda-python; extra == "srt"
 Requires-Dist: flashinfer>=0.1.6; extra == "srt"
 Provides-Extra: srt-hip
@@ -315,6 +315,7 @@ Requires-Dist: sglang[test]; extra == "dev-hpu"
 [**Join Bi-Weekly Development Meeting**](https://docs.google.com/document/d/1xEow4eIM152xNcRxqZz9VEcOiTQo8-CEuuQ5qTmkt-E/edit?usp=sharing) | [**Slides**](https://github.com/sgl-project/sgl-learning-materials?tab=readme-ov-file#slides) |
 
 ## News
+- [2024/12] 🔥 SGLang v0.4: Zero-Overhead Batch Scheduler, Cache-Aware Load Balancer, Faster Structured Outputs ([blog](https://lmsys.org/blog/2024-12-04-sglang-v0-4/)).
 - [2024/10] 🔥 The First SGLang Online Meetup ([slides](https://github.com/sgl-project/sgl-learning-materials?tab=readme-ov-file#the-first-sglang-online-meetup)).
 - [2024/09] SGLang v0.3 Release: 7x Faster DeepSeek MLA, 1.5x Faster torch.compile, Multi-Image/Video LLaVA-OneVision ([blog](https://lmsys.org/blog/2024-09-04-sglang-v0-3/)).
 - [2024/07] Faster Llama3 Serving with SGLang Runtime (vs. TensorRT-LLM, vLLM) ([blog](https://lmsys.org/blog/2024-07-25-sglang-llama3/)).
@@ -346,13 +347,13 @@ The core features include:
 - [Frontend: Structured Generation Language (SGLang)](https://sgl-project.github.io/frontend/frontend.html)
 
 ## Benchmark And Performance
-Learn more in our release blogs: [v0.2 blog](https://lmsys.org/blog/2024-07-25-sglang-llama3/), [v0.3 blog](https://lmsys.org/blog/2024-09-04-sglang-v0-3/)
+Learn more in our release blogs: [v0.2 blog](https://lmsys.org/blog/2024-07-25-sglang-llama3/), [v0.3 blog](https://lmsys.org/blog/2024-09-04-sglang-v0-3/), [v0.4 blog](https://lmsys.org/blog/2024-12-04-sglang-v0-4/)
 
 ## Roadmap
 [Development Roadmap (2024 Q4)](https://github.com/sgl-project/sglang/issues/1487)
 
 ## Adoption and Sponsorship
-The project is supported by (alphabetically): AMD, Baseten, Etched, Hyperbolic, Jam & Tea Studios, LinkedIn, NVIDIA, RunPod, Stanford, UC Berkeley, xAI and 01.AI.
+The project is supported by (alphabetically): AMD, Baseten, Etched, Hyperbolic, Jam & Tea Studios, LinkedIn, Meituan, NVIDIA, RunPod, Stanford, UC Berkeley, xAI and 01.AI.
 
 ## Acknowledgment and Citation
 We learned from the design and reused code from the following projects: [Guidance](https://github.com/guidance-ai/guidance), [vLLM](https://github.com/vllm-project/vllm), [LightLLM](https://github.com/ModelTC/lightllm), [FlashInfer](https://github.com/flashinfer-ai/flashinfer), [Outlines](https://github.com/outlines-dev/outlines), and [LMQL](https://github.com/eth-sri/lmql).

{sglang-0.4.0.dist-info → sglang-0.4.0.post1.dist-info}/RECORD

@@ -1,4 +1,4 @@
-sglang/__init__.py,sha256=3M0oz0ZA8fULhV5LwQ4hxh-MRdHsOJRD1D63C60pdG4,1616
+sglang/__init__.py,sha256=b2oIdWzp5P8SzieeOs2TzJoN3Do3tfJbV8gZS_imVcs,1619
 sglang/api.py,sha256=NdO6cYnklnEBQBKqQjlqI8-P1EownKQ71t5ibCGhEVo,6953
 sglang/bench_latency.py,sha256=oZjSAzX7dUiSu-zdz0dkyUPo-qAX_lsXFH1gf03akgI,76
 sglang/bench_offline_throughput.py,sha256=3OrFI26PmoVTU3pQrBFC50AZI7HpKKuk4vYycbkDjhY,12428
@@ -10,7 +10,7 @@ sglang/global_config.py,sha256=fnT0U9vlHdGaQFKN9tYTnUF4-eVW4HYQURd5zvPtrg0,1286
 sglang/launch_server.py,sha256=4y2QeSj0wVNB9MJQZeahD4ahTDU6gwqo7MPUytyFop0,403
 sglang/launch_server_llavavid.py,sha256=tGc17S1vUfLwbi1GB26oOdXxTWr7gjlqpTrPnrMRNO8,1007
 sglang/utils.py,sha256=r4Dw-xffcrTRposls-gqyoYxjgJNYhVduK_6bDN_Vj4,11526
-sglang/version.py,sha256=42STGor_9nKYXumfeV5tiyD_M8VdcddX7CEexmibPBk,22
+sglang/version.py,sha256=7uCJCJaoOPp2kM9G7GksnnqBLasAAF_4Hm_M-3jPgmc,28
 sglang/lang/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sglang/lang/chat_template.py,sha256=jprS3-In2FTUoedKwZg-HYvDwU8RTIYntOlf2zoN2sU,14814
 sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
@@ -29,10 +29,10 @@ sglang/srt/_custom_ops.py,sha256=Y4gyTDGhWz-W2Igq25Ojm8XFiyvkawW9I-79iwYvxJ0,357
 sglang/srt/conversation.py,sha256=u9zFU8aMYzwHUbQRKU76B_T-jfLlPoxUcWG_nRbDM2I,21201
 sglang/srt/hf_transformers_utils.py,sha256=38Ms0H2-VMerOS6jnczcFtZMS6lhw9B5rSWKAfxVUfQ,7945
 sglang/srt/mm_utils.py,sha256=1ScBunw_x4W8ebM_AcJ62-1T2mfT8NlMJqdAhkF1lb0,12367
-sglang/srt/model_parallel.py,sha256=QR-Alqo0sElDXPJ79N1PhUHHKiEHPQn3dyXduMP-SHQ,3664
-sglang/srt/server.py,sha256=uApz59VUGkRx_HCy6kaiKJFTmaOAvAM3o2yYjEWi9EM,34594
-sglang/srt/server_args.py,sha256=NubTM6ocZY0YDSvPQbvBdURK-7E5kSKHA2Ze09O8_1I,32182
-sglang/srt/utils.py,sha256=p-eYNMVQkw6Yw1b7MBSNWhVvykCuNfejqMjl7cLDq7A,40708
+sglang/srt/model_parallel.py,sha256=1QmoJGzflbYVQ9OpG6YqmtQ6T0QI5HRl61o9nkhvu7o,3570
+sglang/srt/server.py,sha256=Ne7yfXUIST72C0u_f-KoSKLT9PbE9vXtULRa0I_qJzw,34620
+sglang/srt/server_args.py,sha256=TYesukaMQUnv0ru1mY6quU8S1UegxRL0eOCVdaNMyNY,34302
+sglang/srt/utils.py,sha256=F1gffBAjmtLpvvy60Ex38emttpjr0Xn7G1Vj_pzMxtA,42197
 sglang/srt/configs/__init__.py,sha256=_usVIXHQjft4PAJ1Y-yGQOn2QNOv501GYMlQwpGXbns,208
 sglang/srt/configs/device_config.py,sha256=dResqHjkg_dq10v6rnVpbXpvABZRB0jylOm-2_JAnx0,428
 sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
@@ -41,9 +41,9 @@ sglang/srt/configs/model_config.py,sha256=OjEeigs5tMNKP-RImJk2NHVFXv-fyQfsGREWMO
 sglang/srt/configs/qwen2vl.py,sha256=ZjLy9v2eZY4wptUfY3CWgYKg2B5DDrkfCSyTy_Zf_bg,4351
 sglang/srt/constrained/__init__.py,sha256=UWZNVLvOT5ZBX8M36sONgDmnKtkQ0cSfhQD2jO0ATuk,786
 sglang/srt/constrained/base_grammar_backend.py,sha256=FhVm7PxhXDl0joV9NP5RjKgz7dR1dZvUAQnh0mdtvVY,2353
-sglang/srt/constrained/outlines_backend.py,sha256=LmezsMAmTlQgaPqO4Axl4EcSAqKr_ZYZASfAoVxT17A,6670
+sglang/srt/constrained/outlines_backend.py,sha256=CipNHNNXs8xtnJNVNe6FCwZUlSbIXbGmWVlZz3hUpFQ,6820
 sglang/srt/constrained/outlines_jump_forward.py,sha256=iZWXeR3gNYoMubLGyFmLPO4V2YsN5DiGjD71Xk9iFaE,6418
-sglang/srt/constrained/xgrammar_backend.py,sha256=4ZCQgcjWEY2Lg4r2V9sAiYJJblkQ_uVbEnvsjqhR1Pc,4548
+sglang/srt/constrained/xgrammar_backend.py,sha256=qk9tzkoJnp0yDBVdIsB5YIL8PLEF_d8ZsSsv5HQAglo,4471
 sglang/srt/distributed/__init__.py,sha256=__tl9Frrf3PFrSyNYcn5i-y2rL-J4-Qn6RJwrsZ4xgc,83
 sglang/srt/distributed/communication_op.py,sha256=ZoIhboZyefiAwr-1K-wF3rAFSQ4Wt-RxXpsX443Gbt4,1157
 sglang/srt/distributed/parallel_state.py,sha256=HplRH5S0AWdwSdhoHYX9_UWQZlFjh2Z1LHaz68EXlpE,47555
@@ -64,25 +64,30 @@ sglang/srt/layers/layernorm.py,sha256=nRQ1w1xSUcU-zlqVC61BnGG6otS5W1w9VaSzeXizrx
 sglang/srt/layers/linear.py,sha256=dF2HvqiMbhWlCjvkLFRCcgUFGhG-B0keM_CIpjvgTtg,46154
 sglang/srt/layers/logits_processor.py,sha256=oZNu9pNNgmswhuw8irlLm0SfpVrD7cFf-GdfPsLZGHE,13227
 sglang/srt/layers/pooler.py,sha256=rj2lygvleBnyLCBZ8I11HGMgpfIDsT0l3PIkshJwdu4,1606
-sglang/srt/layers/radix_attention.py,sha256=C_mK4mfmKlxMRNeKYP9E5R3PRd3eT-OcE_g3mo36dJM,2058
+sglang/srt/layers/radix_attention.py,sha256=tqC6bqQYqKpdWLoL9j8jmZzgBAMX0XKcKaPlgfJ0uhc,2115
 sglang/srt/layers/rotary_embedding.py,sha256=29tx3JNR40AoXqBa2cFGBjva9vU2xgFipETlpMaaZas,3985
-sglang/srt/layers/sampler.py,sha256=_enfER8MSxsCYrR6_NgyFxKA_XqKtii_asOZUFUUsd8,4580
-sglang/srt/layers/torchao_utils.py,sha256=v0hyr4hLsM42QwOPCdKb-ftRTjVokBZbqvRj4O4C-Nw,3415
+sglang/srt/layers/sampler.py,sha256=yEnAKBFpRcz09Ro1DTQ_C5lUBsSko3DR1jxAFGvnaLU,4677
+sglang/srt/layers/torchao_utils.py,sha256=I1-sUDvfuSymfBk33WpIqz4gHlurh_iey1tO5T23Gv8,2499
 sglang/srt/layers/vocab_parallel_embedding.py,sha256=slGwLiWjuFLCUdRe-GTlfumyZpqVX9VF6No_UGOT-hA,21624
-sglang/srt/layers/attention/__init__.py,sha256=EL1o6Q5vLgViN3pOr2A7F6K9FlNEpMdBypFAVMeq_HA,2445
-sglang/srt/layers/attention/double_sparsity_backend.py,sha256=BlX7uXteQpnoOnKsdBKh8h20zMVMEiibB5F_PkZSlNI,10706
-sglang/srt/layers/attention/flashinfer_backend.py,sha256=q0yPeKUjGbxKnOqbZLHs5fyYkkVE3YEkBBMWtUaiDL4,24611
-sglang/srt/layers/attention/torch_native_backend.py,sha256=amR8xGaaCONvo3M8I4nuYMv6OxPHyYoxu3m8vAqjWfo,10295
-sglang/srt/layers/attention/triton_backend.py,sha256=gjxed2cvc2-8QEHkzyTVv6ui7oYOp2b_vgIUQVD1XuM,6538
+sglang/srt/layers/attention/__init__.py,sha256=KIJhzOJWYioQE7Va4D83-V-ZUZVMZcczuNgDC3dlSRo,2583
+sglang/srt/layers/attention/double_sparsity_backend.py,sha256=RQdEKRykSLf9ilnaHmR6T7RFqh4emH_adfB3aJN2BUU,10920
+sglang/srt/layers/attention/flashinfer_backend.py,sha256=SqwnXV4hstxN-OUev5ZIACHbXwNRHLM7NK85LB-259A,24855
+sglang/srt/layers/attention/torch_native_backend.py,sha256=nQdeqWEMMH_wrod5wssDCJG-uPKm0uslvkALKqPRPQ8,10509
+sglang/srt/layers/attention/triton_backend.py,sha256=HEnmQ14eOsnDkTWhx3r-02PxQfNFDMkGLDXATbEquGE,6752
 sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=BE63WhKiutSNkhJLsRwvfsRy-ExvuAv7FZyoWv73ul8,18744
 sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=1pSXfY3EEaM7iRN_uElHnAfsrJMhTFbu9fj8Z0O2PbE,21480
-sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=Gfct-0_l-S2ZrP4F-zkzNiFbmd3C3f7uJovacOuDxaA,11472
+sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=tZJhzqcf1KKMT8z7_32eVk_D1NHP71c-S3UNxemfAHM,11542
 sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=lojFXRZMLWkzS2Y8uxaolnQhXaWKG19mCAWaF5KQeiI,6087
+sglang/srt/layers/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+sglang/srt/layers/ep_moe/kernels.py,sha256=wb_S2qLxoWWgQu9coXy0XLNGvHzdZSdwXr0PGy4QySg,10940
+sglang/srt/layers/ep_moe/layer.py,sha256=_z_oVTIbHXxz_r7ne0TZdafMn0cdm0mgjQk9_UT3Rwk,22845
 sglang/srt/layers/fused_moe_triton/__init__.py,sha256=PHKFqd2hPOO-g9kSMseg2g76lpg9OGXQDThWU6bt9vs,902
 sglang/srt/layers/fused_moe_triton/fused_moe.py,sha256=qwfRBOeY5DT48Q6z71Eh9cjFehvs_K6eLIVWNL044Ug,28363
 sglang/srt/layers/fused_moe_triton/layer.py,sha256=URDkTt8xEqnqpO5tb_3L7JlhlO53VWfqDDNSRYEu-LY,21545
-sglang/srt/layers/quantization/__init__.py,sha256=0LnBJ2LOtk7HnMzOZm14tMd4Y0eSPSgqUhj9uOn53Es,5961
+sglang/srt/layers/quantization/__init__.py,sha256=Y0rZz3rj6Dg5_QDvsXJd7cZ9NWFFngYrBMA8LuW4WTk,5943
 sglang/srt/layers/quantization/base_config.py,sha256=daK9p0aijMszLUm1W4Pc33FK87MdqYK1NoWFKif-j80,4599
+sglang/srt/layers/quantization/fp8.py,sha256=uyX8U-5cEDLq2XWuG5fX6GKHBla-Z188vi5dgX1dLNk,21975
+sglang/srt/layers/quantization/fp8_utils.py,sha256=eJDLLDu8ZbrbE3BfFIf89JlIMPOP-14DesbeVsajW0Q,1035
 sglang/srt/lora/lora.py,sha256=-o2mBmUvoVpdkgdAkWTARN4kfyep3UNEJLcg6moh0SU,15056
 sglang/srt/lora/lora_config.py,sha256=a2fTQESlCbG1xLiBYy4ptZ6c0Burcqyg1_6V1XSok-Y,1506
 sglang/srt/lora/lora_manager.py,sha256=DHiqdl0_4wQ5PxZBZtlCpP14515mDV2_H9tzL3Rdss8,12886
@@ -90,43 +95,43 @@ sglang/srt/managers/data_parallel_controller.py,sha256=psI4FAuBGjtdnEuwagnGdtRqv
 sglang/srt/managers/detokenizer_manager.py,sha256=TtrtE37XT5XcJzk8-R5rHZ16NHTPd5XZi8hf3h-sB2A,7462
 sglang/srt/managers/image_processor.py,sha256=Y8RgyrzbJjJTpjbnZDa5qiiG5wWjZ68rOXUPDi6kkFo,13698
 sglang/srt/managers/io_struct.py,sha256=d_kctmHcNBzzaP5lUEIpdrVVsob4dNOetMHkobUJZz4,14439
-sglang/srt/managers/schedule_batch.py,sha256=p6OmeCH3arGZ99Ch7JrnTgGU-SsPgjQY7Z6arVzeqao,44998
+sglang/srt/managers/schedule_batch.py,sha256=Zf45mPuz7YyYSSuOXikdjnRfOEG5FE1JKF9OftWxKdw,45045
 sglang/srt/managers/schedule_policy.py,sha256=7QuIsJDRzkrvs3IJk10oOfL4Me0UZwDYvRniT1fSFuo,12620
-sglang/srt/managers/scheduler.py,sha256=fmvwVcZS5DsDdxIJ4bjlLV-qJsRbTxjsqPP5a2SS0C8,59372
+sglang/srt/managers/scheduler.py,sha256=NpBQZjTCysFGZdXvnWG4jqd_eiWrV0a2EUtMpEItDcU,59650
 sglang/srt/managers/session_controller.py,sha256=Yp-IV3rXczACZxZXmF-QxW9CWICGy8KHQ9ttBGJ8WXA,2800
 sglang/srt/managers/tokenizer_manager.py,sha256=XPaSXB6b23u95viFqlqd-tdyrNMMOOiSDWviz_g7UBM,29890
 sglang/srt/managers/tp_worker.py,sha256=X1EwFX3FSsmXx7jeeX2tjZRocaujabQYWm-M-0CFEBE,7363
-sglang/srt/managers/tp_worker_overlap_thread.py,sha256=ZBLCAYz-Ls1coObyO8dNtNsO6gG2rn40KulEmALB_J8,8686
+sglang/srt/managers/tp_worker_overlap_thread.py,sha256=-QNBJRKxraa9Xt2WI1AFzZYdneIJ1eXv0GjFzDqXoE0,8926
 sglang/srt/mem_cache/base_prefix_cache.py,sha256=qEQwEkG4E5rab2ZoTqcesf5pR_J4nV2jBxIHsBJHtIM,924
 sglang/srt/mem_cache/chunk_cache.py,sha256=VcCpyrf5FOQ5xoKeOouCI5ZQLkZo_pgY1SPbDDkagGg,2492
 sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
-sglang/srt/mem_cache/memory_pool.py,sha256=41fjuj_sD0yfJq-sy-X99cc2djBa6w4dy2y47V0WqNU,10934
+sglang/srt/mem_cache/memory_pool.py,sha256=l9_srwXEfIIDF46nxykbHIOo1VSvU5_Ew3H0r5EC7Fo,11072
 sglang/srt/mem_cache/radix_cache.py,sha256=DzLCO_gYQ7X_C2NJSEHzzMZhb5HzWjKF9wXJQsnzr8M,10427
 sglang/srt/metrics/collector.py,sha256=ZWoFx_FKN0sNMSZ8RJWUVQ0RFEYhIHxdw0d4TZTluMU,6861
 sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
-sglang/srt/model_executor/cuda_graph_runner.py,sha256=ffypnhzwAdiBAngHEpK9HVmpvX0H3dFIKGa45tS0IGI,15197
+sglang/srt/model_executor/cuda_graph_runner.py,sha256=6llBpL1Zdb_iNKmcA5yL_ieR0-hP1JSNmUruTiOkiS8,15796
 sglang/srt/model_executor/forward_batch_info.py,sha256=L5mVoW5SaO6To-7nGk0TZM-FFB5_78cARpJ-aC2rwD0,12883
-sglang/srt/model_executor/model_runner.py,sha256=wU06s5tpHgtxitmAWGQC1NjLIcp68iAdbFDWN-TtkBU,29260
+sglang/srt/model_executor/model_runner.py,sha256=cO4KZfaNtbpeDwzNrnHwtyg2UG7iFl7MW6M-sXl-lO8,29523
 sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
 sglang/srt/model_loader/loader.py,sha256=VBrY4W9CiVvS_D8yXhdkW9jReV9rSMSkJplabz0Fxgk,43528
 sglang/srt/model_loader/utils.py,sha256=0NaMR67fESFopaklmsleiL27XH1QUrjZW246MUu1EJ0,1369
 sglang/srt/model_loader/weight_utils.py,sha256=kQo9KPThjH3HAOCfC_tdwdrshdWuWJOVpPR0skSyaRY,24193
 sglang/srt/models/baichuan.py,sha256=PzBOFcEAixakPEkQSaJwC0Xc1fu-yCsN9T0I67r8QmY,14919
 sglang/srt/models/chatglm.py,sha256=DOrEhmb0s-yPId88R6nJeLOTUEtogk-vkB69qT2JdWc,12913
-sglang/srt/models/commandr.py,sha256=-cswAK2_ZTcOsvBkv5Z8SZ1x60cxJryslbSPHDOcnbM,14169
+sglang/srt/models/commandr.py,sha256=PNXgfOZF84h-rSH0edEECUmEGW8YLb44V75Z_oDhFiA,14223
 sglang/srt/models/dbrx.py,sha256=2Wqcf3sv57l4gi2xH8yrb5WSmY-4_kbbf6fhpJ4aKWw,14581
 sglang/srt/models/deepseek.py,sha256=BVNICGoLjQoHmR5lc31YrZ6YbxSRTBilHqlLsALr2u8,15693
-sglang/srt/models/deepseek_v2.py,sha256=2AWdDb5qZ6dj_M6ZY-rCG0omTmerUxbhwuvI9Um4Bg4,31967
+sglang/srt/models/deepseek_v2.py,sha256=YKSrqagVcSUwCAi-rwIph-Xu12GrNETMNKxgnffWod8,35349
 sglang/srt/models/exaone.py,sha256=dkERTZVxrRroqu5AGLP7D4N6n8HvDqlNaDQUIe15mZY,13038
 sglang/srt/models/gemma.py,sha256=ydRqsG-7004r1fAiz01LHUmcj_6XN0Tn4xO1keJnMQk,12126
 sglang/srt/models/gemma2.py,sha256=vPrAasJajitQHB9ZqMFut58xNsOm3fk2m05a-feQL10,14600
 sglang/srt/models/gemma2_reward.py,sha256=hJw0hXNPyQSpazkVJVYiW04OtTZH0GiLI-JJef_kaGs,2529
 sglang/srt/models/gpt2.py,sha256=2je1kE09sGcaORWnJuGYAkcwwOrT9EK-KhQaoCKjCSA,9517
 sglang/srt/models/gpt_bigcode.py,sha256=tovyOdJu2x3LkzmkdFXX_iJdkxuyChIDxwgvPBy6UPo,9528
-sglang/srt/models/grok.py,sha256=lJQEk2D8zyAXE0g4vXLCEmiWM938K_qly02EScwwV_k,13942
+sglang/srt/models/grok.py,sha256=68uS5wuBCc0ClMT2iQl4iGPNbxASLz6c7dCYFrLxGaM,13661
 sglang/srt/models/internlm2.py,sha256=_xcKtd6YtEFUTozaN-yUb0xbSYckRpomfPSKcAk4j-Y,12127
 sglang/srt/models/internlm2_reward.py,sha256=8K26A9oIFFGx_9U2mF87j7FX8K87HGKMnVL3ht1Uc7I,2398
-sglang/srt/models/llama.py,sha256=JVwVDU-8L8RSNOYH0CK8FI557xqjPU2Ts_pQhVfGZv4,19550
+sglang/srt/models/llama.py,sha256=elHH1x3nS_c13Tgx97ExXvbQ9Gzwqg5JCjyQ9qNzmF4,19269
 sglang/srt/models/llama_classification.py,sha256=EdXmiMyfJ9NH5P-Wel7SRhf_v8ddFFhVJMQgzDt0oVk,3377
 sglang/srt/models/llama_embedding.py,sha256=rh-AiczPY_pTpzcACHvSMVjh1hsV_MZBBwP0LQxPsGM,3130
 sglang/srt/models/llama_reward.py,sha256=JVaiTK4gVXNMimeq3kKkv7dt5Hc77hPqF4ewvmzjJes,4622
@@ -135,26 +140,26 @@ sglang/srt/models/llavavid.py,sha256=dYUkKfHoE15vF_VXA_s_ICCTUMSmSgvP181fk8dUi0g
 sglang/srt/models/minicpm.py,sha256=ws4AqhOfAvYHGd04QuXCZel-Oxy9_vN4p4rTjs9RSz0,13723
 sglang/srt/models/minicpm3.py,sha256=YIKJDTpwjmpLlv1sNT93k2yZMvGQlI_H87czjf6QYyo,24707
 sglang/srt/models/mistral.py,sha256=EYifJUUzN2Z2-iL37eJiNZF_DB0H4pa0mKlgYRIxM70,838
-sglang/srt/models/mixtral.py,sha256=KvvtLWn-GLtwbdrt4PBq9gIFJiJH-JFcj0BLfcLcXjo,14322
+sglang/srt/models/mixtral.py,sha256=vi6ssY75kNLy_kJrDru6gJYiAogHjSniaO6aMFd1w4E,14515
 sglang/srt/models/mixtral_quant.py,sha256=uuVO1nWUZJiDhbqZN6gzSMwyfpyZorMuFXHeMCGo7N0,14022
 sglang/srt/models/mllama.py,sha256=3kX-UqeTSYZL5kPNdkfKEAEv3DpSAW1ArAAoeiXVzIc,37739
 sglang/srt/models/olmo.py,sha256=OCDMtX1OI83r80mzU4FMC3Tg8cleQ-7C8Tpoe8zgzss,11708
 sglang/srt/models/olmo2.py,sha256=aC7svioN7XT5owRxPrvhvWBNMON9QXGQBWJ1KHMyXeA,13442
 sglang/srt/models/olmoe.py,sha256=Rw-3YrHWd90MZQFnmcfUQ-3wAaI0PCFKb0DIrCDND3s,15347
-sglang/srt/models/phi3_small.py,sha256=rQFv-4aUGkNPTQjTEME5bcOL9DEQqqFb3aDKrj2joOA,15083
+sglang/srt/models/phi3_small.py,sha256=44_my3QmgJ2N7SOkGZzEb62DXBeCVHojfmCWgkk2uCI,14802
 sglang/srt/models/qwen.py,sha256=_FKDbwaS5C07uJyyivZpBrXJVej4Ph9ivzJdzWJPxJ4,9904
 sglang/srt/models/qwen2.py,sha256=Kh6mW0H2jQdrPS9dJnJShLpo0BNEq6oI4oy5VMHGzac,12444
-sglang/srt/models/qwen2_moe.py,sha256=5-ZTYW5bERhTG5LnNXMqYfWB17NBkvxmQJu6DuDAFCo,16819
+sglang/srt/models/qwen2_moe.py,sha256=rYUk_vZW3ftKIIlqPvJZ1K-6oZ_PfGspixh1zm2Y8C8,16538
 sglang/srt/models/qwen2_vl.py,sha256=3EaUlTbyWOTRXA7eViK1WqmVbCFhXLIpnos49zzf-yM,26561
 sglang/srt/models/registry.py,sha256=inKh9iwOp3LFYm3nqujg-OtABClOP-ifc1stA9cZegA,3434
 sglang/srt/models/stablelm.py,sha256=iBlIkM7CQmqI25nsujWk0LLCQD7TshzUU8qzZYYrt20,11311
-sglang/srt/models/torch_native_llama.py,sha256=dHuUln7RcsRcdyOIUw7HKtOOG9OPmnfOpK8j5gYXzJY,19039
+sglang/srt/models/torch_native_llama.py,sha256=YeXHorFm6QfnczLXwPb5TG9a-He0uiA9RzpR1YZKGg4,18758
 sglang/srt/models/xverse.py,sha256=Oq--KqvbYu2H4TMVGEHpSnJLEwXBpxlncR9ilsQeckc,13579
 sglang/srt/models/xverse_moe.py,sha256=AawKEQw--oAl-yzwCjoaZRG7q3rdkyDiam3FS0zjf_c,15537
 sglang/srt/models/yivl.py,sha256=88OubtuZ38Dxb2LzfV_MTPBI4wKhh4NJqFu--efbhFM,4809
 sglang/srt/openai_api/adapter.py,sha256=gZEaG1dVSFv9WLj0369Ke1yrNNgi_gpgKxPt5Ju9mUw,53775
 sglang/srt/openai_api/protocol.py,sha256=4T9hGCrpfCUSBjKZFvemTfj49CkTUzpCcx6izLv3ir0,10246
-sglang/srt/sampling/sampling_batch_info.py,sha256=YC-KPyDWyLGNPL4YVcst4xwP8Wlz2zcCNJHB_5zljXQ,8470
+sglang/srt/sampling/sampling_batch_info.py,sha256=s--zNjk-LErZ5lMqnZ7KiuJltaziKRbQAU5qYpKIxAc,8564
 sglang/srt/sampling/sampling_params.py,sha256=n7RbBg_bS5fYhsiWa8uJYnfoXy_i5DvtTBOkuFnHDNU,5286
 sglang/srt/sampling/penaltylib/__init__.py,sha256=5vQw0Y5DSzmsoFg1IdMIKLwFVhYZ5ArADHVBYbSmOec,513
 sglang/srt/sampling/penaltylib/orchestrator.py,sha256=J-DEemZcKm1--o37kf3qDOE8SZ_6H3d5oex49Mgq2ZU,10762
@@ -177,8 +182,8 @@ sglang/test/test_layernorm.py,sha256=IacByD5d-stXjzBz8Ypamc7povlcedpKPbb_4JLgo3c
 sglang/test/test_programs.py,sha256=1Z0umrsUu9pagzyGH5SrXl_qhKSyTfUv_kWC2mcn0qo,18208
 sglang/test/test_utils.py,sha256=0lY3ZNfS3JCB4LqSRJgBfB8I0MA8TUT-BJmnrvQC8vw,23797
 sglang/test/srt/sampling/penaltylib/utils.py,sha256=CjxHgywh0hx_87iynzQt_ztHu6zBVuE-YrZ-XPmW6U4,12906
-sglang-0.4.0.dist-info/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
-sglang-0.4.0.dist-info/METADATA,sha256=dXh43Qx9ImYKIF-eB8vuiz_0DDbmNgUrOjCukOXCBTA,22165
-sglang-0.4.0.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-sglang-0.4.0.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
-sglang-0.4.0.dist-info/RECORD,,
+sglang-0.4.0.post1.dist-info/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
+sglang-0.4.0.post1.dist-info/METADATA,sha256=Vfw4EHmIeHM0mE5Eicf11T1xPVOMCpNXsGz1LjsoPO8,22427
+sglang-0.4.0.post1.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+sglang-0.4.0.post1.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
+sglang-0.4.0.post1.dist-info/RECORD,,