sglang 0.4.5.post2__py3-none-any.whl → 0.4.5.post3__py3-none-any.whl

{sglang-0.4.5.post2.dist-info → sglang-0.4.5.post3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sglang
-Version: 0.4.5.post2
+Version: 0.4.5.post3
 Summary: SGLang is yet another fast serving framework for large language models and vision language models.
 License:                                  Apache License
                                    Version 2.0, January 2004
@@ -248,8 +248,8 @@ Provides-Extra: srt
 Requires-Dist: sglang[runtime_common]; extra == "srt"
 Requires-Dist: sgl-kernel==0.0.9.post2; extra == "srt"
 Requires-Dist: flashinfer_python==0.2.3; extra == "srt"
-Requires-Dist: torch==2.5.1; extra == "srt"
-Requires-Dist: torchvision==0.20.1; extra == "srt"
+Requires-Dist: torch==2.6.0; extra == "srt"
+Requires-Dist: torchvision==0.21.0; extra == "srt"
 Requires-Dist: cuda-python; extra == "srt"
 Requires-Dist: outlines<=0.1.11,>=0.0.44; extra == "srt"
 Requires-Dist: partial_json_parser; extra == "srt"

{sglang-0.4.5.post2.dist-info → sglang-0.4.5.post3.dist-info}/RECORD

@@ -3,13 +3,14 @@ sglang/api.py,sha256=vHiKBg8wwIdmrpnGclop5BzJ-1Q88emrlrfLwNCHg98,7010
 sglang/bench_offline_throughput.py,sha256=OQb-AjL4UNymmir02ht43uzgaNsnO_I11nXSowKMqBI,13841
 sglang/bench_one_batch.py,sha256=9-LFvhT0rjNa-Z5L0g5OpKfD6J4sQviRQbos42Fwkmc,18932
 sglang/bench_one_batch_server.py,sha256=8VYNhaQbWGP8TkNVuy_sPjD5FiuVZHamtGRWKwa-Z-Q,5962
-sglang/bench_serving.py,sha256=6SnFF7rku8iDDW2qbIyqgBYsdZ3q3li5YH3zhhQH0E4,57540
+sglang/bench_serving.py,sha256=uTFldXFCArLc6J-ezjHFdM9TsoA9q6nfrjYAGsq5cwY,57582
 sglang/check_env.py,sha256=76itNLUw9KlqbiY1BI4u4YaMZaqyCNcrCLUIb6aHflM,8396
+sglang/compile_deep_gemm.py,sha256=95dhv7JDz-1cYgO0foLflvc7uDsW3EdaPtJ5Ty-BcHs,4367
 sglang/global_config.py,sha256=xzLdk8W53fneFblNh8iIjGF9C3-7mnzR1-LleD9Btxg,1495
 sglang/launch_server.py,sha256=mDXfwha8LHpWQJekcCosR98QhCQsbmilsBlI5jAIgg0,420
 sglang/llama3_eval.py,sha256=gWSboDchIGybIce88bJlrCG0yiLZ513mw4gcutJlzGM,10017
 sglang/utils.py,sha256=GIcgiRHkZ-gyPxXOdn1qFF41jkg4-YdDxbPc4mzO-qk,16159
-sglang/version.py,sha256=0X83evIykSgmyAZc6vNVTXV2UQlVTx0omf8sSLruwLk,28
+sglang/version.py,sha256=qJn6r7BVBDslRB6U_6hE4TM-HRFrJeQvVYrIxenjcs0,28
 sglang/lang/chat_template.py,sha256=MwNL5dNTe8g_l2ljZubnrazEgT2xEv-9O2D0Ezwxy4I,19658
 sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
 sglang/lang/compiler.py,sha256=MAuzoOOpb98njJ7Io2SDmFkhTroDYiq0te0ZpfHkMY4,7597
@@ -20,23 +21,23 @@ sglang/lang/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSu
 sglang/lang/backend/anthropic.py,sha256=qXWqqFlk0-nC62QCcYIRjLTc4AHrdTKpl7hCeDzROUs,2019
 sglang/lang/backend/base_backend.py,sha256=tEutGCU5tni1xGlrIjAVvA9aflJBt2duKrIDzqabJWc,1975
 sglang/lang/backend/litellm.py,sha256=ugmL7sfUxkUHVbHtwNzHgdQAEd4UCjNQboFuE3KThcY,2450
-sglang/lang/backend/openai.py,sha256=n47Zq1GTFc5x1DpN6CYL9cF6dfrsM7iJndnf5jRKU14,16331
-sglang/lang/backend/runtime_endpoint.py,sha256=CAVh3X9F80t_2tkJECF__7AdCQtqDg1AHDqIoKIPnvs,16755
+sglang/lang/backend/openai.py,sha256=YFs7pCDK6_DoYmjTa-vgDVdaeE4PYr7E-sIC1q7vAns,16422
+sglang/lang/backend/runtime_endpoint.py,sha256=4pTG1TnOVTWBCh3rMhqL_NP2hsawG9xuPpuDuUFvD6A,16882
 sglang/lang/backend/vertexai.py,sha256=gz0uNYyBb88jbPYz6ZIJ774fefrcbuVdoK33bphUZpI,4827
 sglang/srt/_custom_ops.py,sha256=L7NuEaRD_Q6Q54n0NZnLXgWZURbnn8Tkg4NQedE6zgA,3616
 sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
 sglang/srt/code_completion_parser.py,sha256=HhEUzdL-FVBsOot9tKDKA1l8Gdx8qsF1RRg-zHNpmLQ,5400
 sglang/srt/conversation.py,sha256=WP72AZrZpiqc5RowucT2tW3jVCb1pb4veW_kpwYS4yY,28785
 sglang/srt/custom_op.py,sha256=J1PUcGaeJJjfAjp06BQsLpUkKyR1zsh9MvDiDlqqJsg,1129
-sglang/srt/function_call_parser.py,sha256=buYENeNEP5bhsvD424yGCa9wOqSfVOZSRn6zLiSJp5I,23733
+sglang/srt/function_call_parser.py,sha256=7RSiI3QSzQagB1TZEHxRI7FU0saiL3SNedxlfDP42O0,26760
 sglang/srt/hf_transformers_utils.py,sha256=N2f-gA8yUq-UP_TJT276gNbDNzmddWsmWnq3px6TIj8,9342
 sglang/srt/mm_utils.py,sha256=1ScBunw_x4W8ebM_AcJ62-1T2mfT8NlMJqdAhkF1lb0,12367
 sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
 sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
 sglang/srt/reasoning_parser.py,sha256=JnaEVW0KG1yJpn9uxmrjwErb9imzni05QDFjExryoqM,5584
-sglang/srt/server_args.py,sha256=2K5KQJgJ8T2q1XAnMIuIRTN5p5soFStsHPPb3n5yhJk,54193
+sglang/srt/server_args.py,sha256=pd2vozUFro4apc72-GzTuMINMRZI6tYBfrkxD4uvWcw,54951
 sglang/srt/torch_memory_saver_adapter.py,sha256=KG3wM9-xZsSdsmORofArnNR7hH55GEyFxaderCDcK9w,1853
-sglang/srt/utils.py,sha256=tbigwWXEsPOCD4rrOA4fzdZa4Qcf76GsagmgGW1DX4U,61565
+sglang/srt/utils.py,sha256=2BRFNpnDtnFbYHCUClPlPFY6tYsXDaXFDzmpEID1yjg,62903
 sglang/srt/warmup.py,sha256=FmJiYfjRr3X_eAe7ojQaPoN17LvHpjDmRWRnO-k86AQ,1469
 sglang/srt/configs/__init__.py,sha256=vulncVn70WqIT6s0HaB8p_Q6FjOiaLwNZWpoJS9FIuQ,399
 sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
@@ -46,7 +47,7 @@ sglang/srt/configs/device_config.py,sha256=kfmpPOECqYxcRoY-ko0QZRhyiBWUGP2CMF51D
 sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
 sglang/srt/configs/janus_pro.py,sha256=-QtJ4ZGZiAJb0AkOEcuCHzIKLw23nF8nRk3rdCcoUO0,19016
 sglang/srt/configs/load_config.py,sha256=qs-AxuplouBx2tsv9KGBOLZPbwzuVA4vbktbGP_cRp8,3309
-sglang/srt/configs/model_config.py,sha256=oMXM1CardGkJThm0KgCxxgYnwXaJXFZzmUZIM_wugeU,22046
+sglang/srt/configs/model_config.py,sha256=UXQZnETXzJVU4BJz-RCDBfIBEke41El_vl1K7f3dmCs,22199
 sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
 sglang/srt/connector/__init__.py,sha256=czLX5JOxuMhH-T9eSJzoc1qv1B4z9chyffDRL5I6wo4,1247
 sglang/srt/connector/base_connector.py,sha256=i6i1TIzsz4NbSEkrdMPq-urb2sN2aLAx8dazga4gB9U,2833
@@ -61,17 +62,19 @@ sglang/srt/constrained/llguidance_backend.py,sha256=Kgd-PQVBQlKWsz506OpF_xSdNBhE
 sglang/srt/constrained/outlines_backend.py,sha256=XbmkZSJzJnnY7k11uj8Et3StfuOiFwRs3ID4IRYAA4Q,6839
 sglang/srt/constrained/outlines_jump_forward.py,sha256=Gyubp-FVetxd6wP4FA_kD6cCXIRfr8k_ZDviJyte048,6824
 sglang/srt/constrained/reasoner_grammar_backend.py,sha256=XFxdZqvPofmtCeIMqR10NOyph06HwbdXfiVI8rIoV5s,3646
-sglang/srt/constrained/xgrammar_backend.py,sha256=pWyJL15D7kdiavcAG7_hMZEfSXbNbcxGE68qtrsLFsU,7288
+sglang/srt/constrained/xgrammar_backend.py,sha256=oc3BTTe8mB5Szv_O-5nZzWbKEKFb22oUniqTUZhewLQ,7409
 sglang/srt/constrained/triton_ops/bitmask_ops.py,sha256=WjTen9iuuFWLzkE1mAHQZB9_7aIy5QH8Wjf-lB-Fams,4614
-sglang/srt/disaggregation/decode.py,sha256=cB8Dc4eyH6BfRqwhgEyU3yvCw1XbFBaYlC9UaeMNERA,20948
-sglang/srt/disaggregation/mini_lb.py,sha256=7SJIcXPt-Fqpbs4dj93-4M30zFGY1AOEu6FCGlU1Uqg,7643
-sglang/srt/disaggregation/prefill.py,sha256=gm1VCWXv_s8iy2bR8RCYV1qbtdq8wW1dkoZmCURd3Fs,11453
-sglang/srt/disaggregation/utils.py,sha256=fXFdNQ9Mt-EnKqPfUpjG-f6bQhLKYxwKRppzWvWBBvY,2540
+sglang/srt/disaggregation/decode.py,sha256=FbUKa3qiCGGqRzz5rJiNQMqIFhFj4BXONYRfH80PteA,22812
+sglang/srt/disaggregation/mini_lb.py,sha256=1YTFUV5ovVf_D2RXmvyn21x9kVgH8x2RmmRY3mSOfZI,9630
+sglang/srt/disaggregation/prefill.py,sha256=1MoGATkj89vv9_eBHcMGxAQiyxnow1idvL_IjudjV0o,14615
+sglang/srt/disaggregation/utils.py,sha256=6ackrcitNF94ur9bRvPerF29E7g8uU_0a4-nSdw1EMs,3078
 sglang/srt/disaggregation/base/__init__.py,sha256=KR8xXoRCDAy2U623mfP6ujXu42m1_F9EiudjrKu2I_A,130
 sglang/srt/disaggregation/base/conn.py,sha256=gpf32bhYXWm_iaYB6WcrDaJ-UoL1ZzPI_xpi5pMhRQo,2443
 sglang/srt/disaggregation/mooncake/__init__.py,sha256=1vacEHmWjf7zgbMPzsXKB08FqNKNCquJdUiDlO41BOk,122
-sglang/srt/disaggregation/mooncake/conn.py,sha256=byeMgsi3Ape6sTNbF9KIvuq_R6FZMaCwEk5VoLqzeUg,21117
+sglang/srt/disaggregation/mooncake/conn.py,sha256=3byp9qhu9fCcv1_HAK-P0fZB6_o3sC6Qq_i0tbLItkM,21250
 sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=MxDAB9ZetRF1pFS2LP3FVHPtQ1HjIt_SK3UMaYHZ94o,2604
+sglang/srt/disaggregation/nixl/__init__.py,sha256=n9HjrRk36WUcZNeetGWOh2pSriLp7GNTq7YYX9K3EtY,85
+sglang/srt/disaggregation/nixl/conn.py,sha256=ZFyKZQtGrTw7lNi9BYNlfY-1idHFzerTfvVNHG2Uj5c,22652
 sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
 sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
 sglang/srt/distributed/parallel_state.py,sha256=hoTgLYfHIKMb_tSwBTauuusJZ8oY9BsiubTTOF8UfIw,50713
@@ -85,26 +88,26 @@ sglang/srt/distributed/device_communicators/pynccl_wrapper.py,sha256=LblisImY9d6
 sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=bbruDIM1GgKIdB6gi71_I0mpB179I-qyvwKuSj1Kaic,20816
 sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
 sglang/srt/entrypoints/EngineBase.py,sha256=xoyvp6XAeDLY2_Q2Ng33H-fRhrXHv2ldJJKd-HuDhqE,1870
-sglang/srt/entrypoints/engine.py,sha256=cO-Yq5i_hrn_yaAuhkHKkUUVXQmHXcTV4B-l76LjbwU,22137
-sglang/srt/entrypoints/http_server.py,sha256=wYjyyiajP6SWa3auZHZIUJv30zioB0IwdFKXHlyT5zo,28431
+sglang/srt/entrypoints/engine.py,sha256=-qHfYFDremLj8GhwQa7GuWHQKop7Tyq2HvmBXULtCos,22282
+sglang/srt/entrypoints/http_server.py,sha256=vhrkH8N0Vc8xwaRkNsz13ptQ2uRnrZ8ggkOiC_bhW70,28353
 sglang/srt/entrypoints/http_server_engine.py,sha256=ihA6y3GXRs28Y9U3SgdQcJQjnw_SVIby7QrVgiafX04,4846
 sglang/srt/entrypoints/verl_engine.py,sha256=XLYdwTwhH0jTjw8xczgZXWfBXMRb_ur2bg4TN0dTwfI,6975
-sglang/srt/layers/activation.py,sha256=pshilucJ66qSotOjvP7p3LmTBPVY6xBKkbwEpTLX_WY,5974
-sglang/srt/layers/dp_attention.py,sha256=Tfw2BydGPAeLcDlyl0jzBLOtkiygJhgAcf63RGZhrEE,7535
+sglang/srt/layers/activation.py,sha256=oSkdo8B8najXFcVay3Y__CEvgXh87lAIhG0CMp2Ugqs,5954
+sglang/srt/layers/dp_attention.py,sha256=WJgXg_KyBzDHkwyfUFBowpDRFd0q5Q9LgEhqT-qT_ys,7549
 sglang/srt/layers/elementwise.py,sha256=XCrR2i-9dP-H6jQo2zUuquwZrsl_wEQqj5Wxk6WUf7o,13987
-sglang/srt/layers/layernorm.py,sha256=Z0N8S6vUX8F9SmPQi80pjaa6KGw5YJZYuVEqfgiZGV8,4546
+sglang/srt/layers/layernorm.py,sha256=H5hD0OPHNeNBKkJcFsm3unOERJBNe-s1en4S3GAILzI,4936
 sglang/srt/layers/linear.py,sha256=nC9MxJrFap1BEyqgFlBySH4IeQruIbcBp32cOhUl5Fw,52149
 sglang/srt/layers/logits_processor.py,sha256=Vp8ibljVEezTr54xzeOcjiJR7JdYO8ItkO5nLIIMVu0,24206
 sglang/srt/layers/parameter.py,sha256=zqWyEzpWzP4NNTjq3G9khq6XofgpcmJqQLg6Vd4WyWE,15084
 sglang/srt/layers/pooler.py,sha256=rj2lygvleBnyLCBZ8I11HGMgpfIDsT0l3PIkshJwdu4,1606
 sglang/srt/layers/radix_attention.py,sha256=xcsEmKLZYu7K3RaYnMX67H86XLiKD8AGu0Ob-4oV8aU,3247
-sglang/srt/layers/rotary_embedding.py,sha256=-LXRtNCoawKiKwrtyhO91bMRBxKf8Vh06fF4P0zSJ0Y,45775
-sglang/srt/layers/sampler.py,sha256=pvtlV2L5RYiwsCr4A0tE1h_nou9grFbktFR8bcHMiLg,11404
+sglang/srt/layers/rotary_embedding.py,sha256=voz9dM_9f6uVww9FuaUkwYDFJ_U0r_dXsdv-MaWvX18,45705
+sglang/srt/layers/sampler.py,sha256=PNgMXm2vsNsE6Rt89R5GLDC3lDxdIujoWli8F3vldng,11384
 sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
 sglang/srt/layers/vocab_parallel_embedding.py,sha256=QUxd4sELx6p3dHvEKmccPZ-phdd_9EjNdwjH3SJ9zxI,22238
 sglang/srt/layers/attention/base_attn_backend.py,sha256=X_GIbQuU9njtUEGdUP7E_KRhmGxj3UyPHNESlL3QaQ8,3264
 sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
-sglang/srt/layers/attention/flashattention_backend.py,sha256=9dv3cj7fRODFbc0v2pRLxmkFcSfLH5M-iVU_PpfaP3A,51364
+sglang/srt/layers/attention/flashattention_backend.py,sha256=YEWvK6Q3KsCH3YLbLZ8k2IAN1U_vvvLlZ9wE9aZKxBU,82342
 sglang/srt/layers/attention/flashinfer_backend.py,sha256=YtMTgMhxxNrAbSoWTPJczgY4SR3WjnAPXPoJ2d5PUZY,46394
 sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=pnVhvVEK87iFW8gUb1G7X7c1tqro8R2DSEOFCnlV8Bo,30301
 sglang/srt/layers/attention/flashmla_backend.py,sha256=1RPFNtQOBw6BWxIjrzfJgA9Nx92udLbR-S5KXmqjxS8,10536
@@ -113,16 +116,16 @@ sglang/srt/layers/attention/triton_backend.py,sha256=oEEiUwHbm4rNw5ExbQ2c3n0TwAg
 sglang/srt/layers/attention/utils.py,sha256=J9mA-cbZT3uTlaKXo0HEAaeMei_TS2o4McTna9LVDCE,2750
 sglang/srt/layers/attention/vision.py,sha256=H7dQofAlZjC48Dr6bo4HBsZSLDhdrbHKChyGejeaEGo,11886
 sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=DPu_aCPgwPqKWZPEQmp_xA7MPbpV2ip-MEICCB470Ao,19120
-sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=BXUY8ARHBF2s9x9waiEwfZwcMgvuaJA0gxb4OeUZ_tY,31167
-sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=6MOrfQDVJQMTUXv0T3vUSF7JA67hVXxWqIbfDGBdKYM,13965
-sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=Y66gZ37u0GKMPtI8n5MbO6uOxRuGEmKIG0IPbJTOqAM,6213
+sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=vsDZZ5QGb8-KBzADgKshnVQbsW8zRJF1h5hgdPGW5lU,31124
+sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=m12jEnQkNJguATqvZ57HtMC2hhU4wqdB8xAYdh25BxE,13922
+sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=waZsmpKIp8rTgFSoM4QMabJuLaB3yW6ltOzAKJksBoE,6260
 sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py,sha256=664WnAJ91EiCUZOcnVDfbTQf4uGJ4ZDZB1CbxpEUFZc,13866
 sglang/srt/layers/moe/fused_moe_native.py,sha256=IWoRLIEMhXH8KAB9jt5QSnhUtHn4SnbJ9dDO1LNTZ9o,4659
 sglang/srt/layers/moe/router.py,sha256=5Aeqoix_AS4uymb665OJE904wVSBkQeFdZP4e7KKPvg,10530
 sglang/srt/layers/moe/topk.py,sha256=K-VU64nWBV07bu1Okn-uYbhz9gylq-KFNRYn2SFzu28,11129
 sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sglang/srt/layers/moe/ep_moe/kernels.py,sha256=ijqRzS-tb0LGnDU5hW-g0JH104ppADrWaUIDGxb9Feo,22919
-sglang/srt/layers/moe/ep_moe/layer.py,sha256=Qotud38bCHg1tUtNKNjHPl4yHAD8ofELjtb8zcoePss,36350
+sglang/srt/layers/moe/ep_moe/layer.py,sha256=SZ0shPwgDp7xj-TCv9bfg5O7f2AXjF6xmBP5xkZ0Ips,36440
 sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=zQV7Qr-Zrcr3D3efVvZepRQM02bj5djHPsijPssavk8,20430
 sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=h9yMFAL_bagUf-qBED8gSWdCOb7d8IdA-pE-L_nIg8E,842
 sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=DRkGQ6vuk4d786_UWMBqYlw-9o75k-T_rdtLQLZldK4,55410
@@ -265,24 +268,26 @@ sglang/srt/layers/quantization/__init__.py,sha256=UOQcyCvKFkX0u_OPPex7X5X98iUR3l
 sglang/srt/layers/quantization/awq.py,sha256=VImnVCU_QBLFba6S88T0dJ-vLy6SMm3OLIMEdllDfVI,6663
 sglang/srt/layers/quantization/base_config.py,sha256=jWk_egQrVNMYmQgbTI9vkcgzScLFjB5_sywFlAfE5J0,4776
 sglang/srt/layers/quantization/blockwise_int8.py,sha256=cu9-JiCZDfMfvB97Kv_-eEG87VX5bRFIllFkzpO_xIg,15122
+sglang/srt/layers/quantization/deep_gemm.py,sha256=xYDc5nh2nD2R_Apw0r4Swd3IYDzk3MGo8xlkV3W-Xl4,12800
 sglang/srt/layers/quantization/fp8.py,sha256=Niu89OfZd4pIpkwZ1zd2Hrlffx0c5L5zkix6Lzi0Vys,40970
-sglang/srt/layers/quantization/fp8_kernel.py,sha256=oYq-j5moiilrTndKTqF4mRxCvhB1nSYhPMC9VeqcR4w,32964
-sglang/srt/layers/quantization/fp8_utils.py,sha256=LwP0Z8jPlaWpGBKVd27xqSk0ATzuB9CeLNEXiPm8wXs,18583
-sglang/srt/layers/quantization/gptq.py,sha256=e4rMz374-yQQqeAI77WPxfcAaRk38GeN2akEpvnC_Do,15141
+sglang/srt/layers/quantization/fp8_kernel.py,sha256=C2_hOLRO27-Yvjy-Nm2niehD2gWSMuP6TnNX07ESqh4,32018
+sglang/srt/layers/quantization/fp8_utils.py,sha256=1AmKsAFlpPcwbqpFR6P2CaCOvpp8dYY7lzXLoKjVikE,18631
+sglang/srt/layers/quantization/gptq.py,sha256=gyGMOPXHzozK7pPWSjKgLdFX9h7MCEww7n8FqEVEVac,15364
 sglang/srt/layers/quantization/int8_kernel.py,sha256=GfRn_imIw8kNgqdtb2lr7BettjgDgimbl1Rubnamjh8,11352
 sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V2giDg5G5VKrpcUA,2356
 sglang/srt/layers/quantization/kv_cache.py,sha256=-yaFTdB75T0BbvQeuIpH6rZoL3R8t6OIJVGB-xdtpCw,3492
-sglang/srt/layers/quantization/modelopt_quant.py,sha256=Ff7qMv7CCWj0QY5gkDnwlQYLH1mbMtopbw8jXMLndXg,16616
+sglang/srt/layers/quantization/modelopt_quant.py,sha256=TpPgtbV7O5r1JY4Wm0np2pReQO6XERIdEDQcV41oTn0,16596
 sglang/srt/layers/quantization/moe_wna16.py,sha256=KtFr4lIslMA12yx4JjXXPOsa5OHjxXWA6scYCRQnFMQ,19483
 sglang/srt/layers/quantization/utils.py,sha256=3fP11UCSWkFWW7oTfQ6_3I1ZXfHvRL4WIlTAXnT1Ues,5442
 sglang/srt/layers/quantization/w8a8_fp8.py,sha256=VhM36MKz02W3uPCi-9Ap0XpQPXBdL88ny3l_aEtUq2M,11766
-sglang/srt/layers/quantization/w8a8_int8.py,sha256=_oOJMkMrRMU2WvzAsNsQubQaVYcJJx9kr7Pps5MW2dw,9002
+sglang/srt/layers/quantization/w8a8_int8.py,sha256=MkvmcxQj3X5AZbx8pgnHYAikc_Xd_jOhJXaxx7255ho,8984
 sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=ssrSfCJ9ORpxsXNfCiKioxmrwY0alPTPd52YLEqiqlk,25634
+sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=EaOKuIA0zXwqmH_eVhWeNdGJT9d1d9gVvFyYkgpdjDg,25665
 sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=no7gs-M8eEYvNd0XPoVudfb1mBweoSFfcHYoWytJeAY,26199
 sglang/srt/layers/quantization/compressed_tensors/utils.py,sha256=mnUmKWFQUnY8bVoFHUuNVwqsfS-cefeR-ofyaihCXcY,7621
-sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=qcdRgoUNJWXqSimns-D987TW0OTk3uFuWNBX8Z6H8Fk,246
+sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=HWMTnmrj-mUCRXgcOwnnXLrvrAE-ONdPTSzSImjHCMA,347
 sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=tdKJC8c3SX8T3z8JL-1YCsg4ftcv55Wxt0vZrYftpX8,1635
+sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py,sha256=-iq634sU38yWFA-h3w-B4kTALeXMo7uRZQI6CckMZTo,5494
 sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=NZurhURFpZKqfMfgyd7oHLTLThm_8AO7xBCY8F6i3Gk,5881
 "sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=RdHQxWXwXqvio31192vsLaKjEr4f_DjpMPKlarY1IAk,3251
 "sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=0vLaJgo5B9ti-XMFKJuvSoMGjsZQ-RhHSx4cC8Xji-U,3254
@@ -452,19 +457,19 @@ sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=ZmWEqHJaorRNNj-c_ZXPi_pX8X_yIA
 sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=Q58UzWUb3QFqY_ZxWA3poN373N0Hwkks5AQRKIuvFC8,4517
 sglang/srt/managers/cache_controller.py,sha256=d4RGqbut1FlzJnpqr7WY_TYmRjYPS07OoOVbztjs5xI,18959
 sglang/srt/managers/configure_logging.py,sha256=fOJaXAQ1n9m-8KPJndpsKvS885i69SMafoEADLIVfIM,1633
-sglang/srt/managers/data_parallel_controller.py,sha256=Xkj2n9uDyq7a-AVDZlfzeuNkC4ibsSftb1_bed9hgQ4,10318
+sglang/srt/managers/data_parallel_controller.py,sha256=yKP4Emi5gEGIj5Z6jq2WZ-hRsPSXIb_tVnoYOx4g_pI,10583
 sglang/srt/managers/detokenizer_manager.py,sha256=3S3aRvKSi75RQSxEEQkeyxKDNNunWiw9wlwsbT1VXSo,10099
 sglang/srt/managers/expert_distribution.py,sha256=r3o5RGI0gnV7xb60AApqKYa0oiSB37oB7hQBX7P3xZM,3225
-sglang/srt/managers/io_struct.py,sha256=nNRAJXJpJvZFHFkOPHVa9TkzawlhZlfHpu4qlZsYPWw,30897
+sglang/srt/managers/io_struct.py,sha256=K4ciMrIREZ7RbuhLeaxYrythW3JL9NJ3uzyAOKATk54,31252
 sglang/srt/managers/mm_utils.py,sha256=P-UbCdzasK0yR-xn6Lrk3ILct3uJrIBuXSDrtRZlB_A,15542
 sglang/srt/managers/multimodal_processor.py,sha256=XlRYvNhF6XOssreRX9DZPhLSpps_VE62gSKw3EGdNPo,2088
-sglang/srt/managers/schedule_batch.py,sha256=pPKw8z7B_6tA9OZoMU2r_KPJzAx3aNjylZx2Hm1bEcw,62407
+sglang/srt/managers/schedule_batch.py,sha256=Kn5dP1Q8fiRRkCMQ29u0vJ49EV2f8cv3Rmx8hAuC_FI,63112
 sglang/srt/managers/schedule_policy.py,sha256=E1qVq2G3jptKdX9nlqfayeRBUll9xB6bK8nBf3EW32E,19469
-sglang/srt/managers/scheduler.py,sha256=SujQHQOzw-O1NDxgMF8JWI0nF-EdRDC2ynKOXp69cNo,79876
+sglang/srt/managers/scheduler.py,sha256=BfobLcO8xH4PuLGGEJeDn5qinBEUws7_PofULNfC7f8,80361
 sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=u2sj6MViFTov0lVZSysZ-wph2pEqRCtCjwA1UdttZ7I,26338
 sglang/srt/managers/session_controller.py,sha256=o-ifit0n4_xHLNmyD0Ams8FxGRgxFybX-Vz1hwgr3UQ,5755
-sglang/srt/managers/tokenizer_manager.py,sha256=ukKGBjsVdI-FS3NF3sywxAHpWvK_eEOCDsfI0mPPPqw,46706
-sglang/srt/managers/tp_worker.py,sha256=khF-hXOrtF_IesOyUSjEBjb7fAh3CakdiKR7Ebj2wp8,8894
+sglang/srt/managers/tokenizer_manager.py,sha256=dTD1lgPOJ6aBcxeT2eg_ZzQELgbdmYmIOmApTiiTpWU,50553
+sglang/srt/managers/tp_worker.py,sha256=OV0Zc-oK-HXSWO6x26ItDEf-qB2IqyJq2z0TFuBZz0s,8970
 sglang/srt/managers/tp_worker_overlap_thread.py,sha256=3_ZJ8Rq7v2ZDaRNTRu5Dy8AbqiAlJQp3IAKnn_WAwd8,9127
 sglang/srt/managers/utils.py,sha256=5i75uLlQOF_5CaT02CrWtwozMTtwTg2_nLP8Dtr-JZQ,1536
 sglang/srt/managers/multimodal_processors/base_processor.py,sha256=M36x_Emm-IdpFiQpii3qyQZ79O7NZsyJgDT5gk08Plo,9923
@@ -480,15 +485,15 @@ sglang/srt/managers/multimodal_processors/qwen_vl.py,sha256=67EmFiAkvZncU-eqiiS0
 sglang/srt/mem_cache/base_prefix_cache.py,sha256=NY62Zo0A0tLJ7ObRLOQqQcXCxoJUDZsK8f5U4dNQjKc,973
 sglang/srt/mem_cache/chunk_cache.py,sha256=it5SfL1FwMbrdeOH-I-Eu_i-I9hFB1xL-z_brIUoCkk,1835
 sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
-sglang/srt/mem_cache/hiradix_cache.py,sha256=hCexDvC_BC5juQHAuzZRE4e9Stirq1ysfsB87uz5BcQ,16340
-sglang/srt/mem_cache/memory_pool.py,sha256=bMzNK-8avd-_rwKqTJHwMiQKXP4rrt6MmXbofFDWihQ,31753
+sglang/srt/mem_cache/hiradix_cache.py,sha256=BJR-R2u5YyYIhGIxTY-3rf8Vx60XjCRU8Yhmkn2fzzM,16597
+sglang/srt/mem_cache/memory_pool.py,sha256=wexD6ojsN1tT_jtIa5uRU7UIPa6V0Zg1KNKJAa09aww,32338
 sglang/srt/mem_cache/paged_allocator.py,sha256=BrJS0vN1k-vTSgb_M8u_1KoZFRgzgR1WRyImCTq3T0U,9770
 sglang/srt/mem_cache/radix_cache.py,sha256=Lm-pco6CJ4orb9IfDpbHm5MnyK8Ya0OF1x9p88dv548,14906
 sglang/srt/metrics/collector.py,sha256=zHg4twFQJvuK1mSme3-EYQa9PJryfp_u7a4RxQ5RcO0,8874
 sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
-sglang/srt/model_executor/cuda_graph_runner.py,sha256=ZaN1yPju52iOVQwfCVju2Iw_ci4B87mI_xi21IZFZis,23325
+sglang/srt/model_executor/cuda_graph_runner.py,sha256=lGnVuRqm7f34q79gvCbXoHCQcZyK14Xq_hXzWLP9cjs,23550
 sglang/srt/model_executor/forward_batch_info.py,sha256=_qSMTiLxvcPIIgqRfUqG4W--OoirVY7ulcFfZqQIqjo,28689
-sglang/srt/model_executor/model_runner.py,sha256=mDPja0tc2NNa2UBf1GfpjTtowmCdDncSS06NkwzFnmU,46476
+sglang/srt/model_executor/model_runner.py,sha256=nOyU8BQmQz6Y67HS2D3AcA41mABtjeAYH8xVgjLoFdI,47104
 sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
 sglang/srt/model_loader/loader.py,sha256=YYmtvkQw0B1qgPw0_gN-K4yy7CEYbTSR__0Dl1Fnm6k,55342
 sglang/srt/model_loader/utils.py,sha256=0NaMR67fESFopaklmsleiL27XH1QUrjZW246MUu1EJ0,1369
@@ -502,7 +507,7 @@ sglang/srt/models/dbrx.py,sha256=4pn_fdoATg01VEqNnIAxNEsKV5XU7gwHyd289eydq1s,155
 sglang/srt/models/deepseek.py,sha256=m8CjJIJiQ9B_ACPy7dwMLfm4kVLXcuW27zDk_lcQ_Dc,16920
 sglang/srt/models/deepseek_janus_pro.py,sha256=8wAzvcGdyo--3faMN4QtagT1eAZMhMFduvpCXqUS48Q,70456
 sglang/srt/models/deepseek_nextn.py,sha256=mL2nnblFmeBD8cSf15BmJh_M-8dyCx07sqlicw4rab4,13454
-sglang/srt/models/deepseek_v2.py,sha256=dAjHJ_2aRZSd0OQ0uCinDmRYpVs1tEWEeDfXy_NrdxQ,68369
+sglang/srt/models/deepseek_v2.py,sha256=0GERrciRWktKyIwscFA0HPvm_XdElXxaEpJ0kY3SoGw,68497
 sglang/srt/models/deepseek_vl2.py,sha256=RVvi_3qsfrkqMCCnjjTA8OwUc5ySutc7asAH-rUJLVo,12922
 sglang/srt/models/exaone.py,sha256=rX7J0xFt9TSt6tMIhnYMkb5KDnqTJIV4BtjPLFwQ8_8,13425
 sglang/srt/models/gemma.py,sha256=4cdrPISg1VKnsuI-QPTpYvet4BrX8BMKvCIN82iLskw,12641
@@ -526,8 +531,8 @@ sglang/srt/models/llama_reward.py,sha256=LF2nqMV5XOrljGjAwJg43mBv3z6Q040I2EYlgZe
 sglang/srt/models/llava.py,sha256=KMwNNrlMuMaKEOZMDRBKBQbe6uctpKTLc0zOceyGC34,27242
 sglang/srt/models/llavavid.py,sha256=q0lHlRnoYHKJZsWnkIQdd6dYAQ26t7XsmrqA0zDGmZc,12829
 sglang/srt/models/minicpm.py,sha256=m5HFsSJj0Po09LY9R6qj6K4gceqWDMOePz3NDGgMGT4,14691
-sglang/srt/models/minicpm3.py,sha256=R5-9CHgyUnsnxYPwLP7LQA3AKQ10Igtphs5x7u98Oa4,19367
-sglang/srt/models/minicpmo.py,sha256=kJnp8UwJTV7kXEpuVWA50ecRsuZyFedHlwkprix8tag,75619
+sglang/srt/models/minicpm3.py,sha256=6-gfHSfXwyB5zw7AIj-c5TzjpEKR6CM0H67MrD8LVUE,19347
+sglang/srt/models/minicpmo.py,sha256=qSs4c8aOU1W_V4fDYtcboWKFPF06NIw-h9rWozob7JQ,76204
 sglang/srt/models/minicpmv.py,sha256=79zZn3co9r7SERatx49EuHRoLWRiy6qeaUFgjDWJo2I,40571
 sglang/srt/models/mistral.py,sha256=EYifJUUzN2Z2-iL37eJiNZF_DB0H4pa0mKlgYRIxM70,838
 sglang/srt/models/mixtral.py,sha256=zQHCL_ZMKmLR7jitpEw8n7Rv6xhxUJzSXklsw6auh2E,14965
@@ -554,8 +559,8 @@ sglang/srt/models/torch_native_llama.py,sha256=5tfFSMAXB3ScToqTALtCXa8Oo-qPCJh-K
 sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
 sglang/srt/models/xverse_moe.py,sha256=7KCM2-j12towDMNvXkuuYiBOmNauH6NG4Ip40x0khqA,16782
 sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
-sglang/srt/openai_api/adapter.py,sha256=DaSU4Pri70s3ZeMHeVzsnKjd8dA9lx_HOmpVs1TEepo,72095
-sglang/srt/openai_api/protocol.py,sha256=Y8PFFhLbzhpoERM6-WsTkm-ZuGcE-3tfenh9e-AC1vc,13374
+sglang/srt/openai_api/adapter.py,sha256=t5SqWVLz3ASJx_b8K8JkjXcq7qVopDlOBPOswHNig_4,75232
+sglang/srt/openai_api/protocol.py,sha256=1IVfYt0LUNLqFz0DNZyqxU02IRYVHcL7jnpMG9bNq34,13532
 sglang/srt/platforms/interface.py,sha256=hym3iooBB4C8if5hDZezgVN6h4NIOu7sg2ZUBIV6XmM,11246
 sglang/srt/sampling/custom_logit_processor.py,sha256=tDvoLgLqn-sy1qcY6vSrpbnHCeqbdk0uhMOO-uy4p4E,1099
 sglang/srt/sampling/sampling_batch_info.py,sha256=4LCowU2bk0TOSfIGpEy90N1SpTsiOKK8Rx1ZYcklUFQ,11988
@@ -565,10 +570,10 @@ sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZH
 sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4TO2OoEi___p-i3QdwkgU,3331
 sglang/srt/sampling/penaltylib/orchestrator.py,sha256=XM-Lm6u7gYPtMZrTIc0FR4QxNZxBH5s_Cj82umyCzYk,5721
 sglang/srt/sampling/penaltylib/presence_penalty.py,sha256=NRh10AJrrQlGJ6S-enGdRefrTrWpyqrSm-aNnyqQNQQ,2119
-sglang/srt/speculative/build_eagle_tree.py,sha256=SFQ3eHbhfNxOdxgqDP5wSV_ZlIVqLw7VivycNZ963N0,11690
+sglang/srt/speculative/build_eagle_tree.py,sha256=lt4sXUehPi26MT2-2Z0VivtF6AP7kirSaEO_u-YJ4J4,11670
 sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=FP-Dc6K4zaL2KQA8QsNccBM8TXnwREh1I2iPL9KHo8I,9252
-sglang/srt/speculative/eagle_utils.py,sha256=mv--nBUgAbqP30pU3aGEMwQIHBwwevETUMQSZAelApE,28721
-sglang/srt/speculative/eagle_worker.py,sha256=iQ7E6RLNyxXNs_jqbQ8SpdaXEMIC-ULBslrY9iMTv3g,26865
+sglang/srt/speculative/eagle_utils.py,sha256=iJYhklXHfDgEKbVB39HkVEea-XTEC60Z_LjIVjkrZQs,28701
+sglang/srt/speculative/eagle_worker.py,sha256=D4G8hnwtc8xQt1okG4TY9wYSXbKTqGVDAD22AUXW6pA,26824
 sglang/srt/speculative/spec_info.py,sha256=rhaKG0TzyF9XZYHEWp1jccwTBohSNsUDvxHFtAoOl18,709
 sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sglang/test/few_shot_gsm8k.py,sha256=7VLbWl4nCQs1wjtW4q-46jf9jUCycSs5Iw8v7sUSzBw,4284
@@ -589,13 +594,13 @@ sglang/test/test_custom_ops.py,sha256=2bSo9P5_rJZYFq8Y8IKRimDfFyZZGJluhL7Ngny0Pf
 sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsuFDs2NolI,1638
 sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg,3764
 sglang/test/test_programs.py,sha256=VZ3vXtUDBnXz0M7gFdDH8hXg9Wa0j_qI8CVqjEgRN_E,18877
-sglang/test/test_utils.py,sha256=Y7XMx8-BTQJr6a90qRVpK4x9Lkl_p2WyL0VwFNHxhPs,30530
+sglang/test/test_utils.py,sha256=xk_o4zEDSNSy88Jiy7RA1fNfnBlYL-V49EzrLlf9bvM,30643
 sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
 sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
 sglang/test/attention/test_prefix_chunk_info.py,sha256=er0i3KGHMkw-4UZB1GCFd4oYwRcXfU5wpO1ORqpNGGA,7626
-sglang-0.4.5.post2.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
-sglang-0.4.5.post2.dist-info/METADATA,sha256=C7YpNRcr_rgjjRxghmVgh_lQdH7BCAgvIZqNYLag3zU,25592
-sglang-0.4.5.post2.dist-info/WHEEL,sha256=pxyMxgL8-pra_rKaQ4drOZAegBVuX-G_4nRHjjgWbmo,91
-sglang-0.4.5.post2.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
-sglang-0.4.5.post2.dist-info/RECORD,,
+sglang-0.4.5.post3.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
+sglang-0.4.5.post3.dist-info/METADATA,sha256=aRgCmz8aysjesjP6QgqwsO3k3oLNVOonYv2-pl7GAE4,25592
+sglang-0.4.5.post3.dist-info/WHEEL,sha256=pxyMxgL8-pra_rKaQ4drOZAegBVuX-G_4nRHjjgWbmo,91
+sglang-0.4.5.post3.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
+sglang-0.4.5.post3.dist-info/RECORD,,