sglang 0.4.1__py3-none-any.whl → 0.4.1.post2__py3-none-any.whl

sglang/srt/speculative/spec_info.py

@@ -0,0 +1,19 @@
+from enum import IntEnum, auto
+
+
+class SpeculativeAlgorithm(IntEnum):
+    EAGLE = auto()
+
+    def is_eagle(self):
+        return self == SpeculativeAlgorithm.EAGLE
+
+    @staticmethod
+    def from_string(name: str):
+        name_map = {
+            "EAGLE": SpeculativeAlgorithm.EAGLE,
+        }
+        return name_map[name]
+
+
+class SpecInfo:
+    pass

sglang/srt/utils.py

@@ -1273,3 +1273,65 @@ def dataclass_to_string_truncated(data, max_length=2048):
         )
     else:
         return str(data)
+
+
+TOOLS_TAG_LIST = ["<|plugin|>", "<function=", "<tool_call>", "<|python_tag|>"]
+
+
+def parse_tool_response(text, tools, **kwargs):
+    """Parse model response containing tool information.
+
+    Args:
+        text(str): model response in string format
+        tools(List): tools from user request
+    """
+    if "<|plugin|>" in text:  # internlm2
+        text, action = text.split("<|action_start|><|plugin|>")
+        action = action.split("<|action_end|>".strip())[0]
+        action = action[action.find("{") :]
+        action = json.loads(action)
+        name, parameters = action["name"], json.dumps(
+            action.get("parameters", action.get("arguments", {})), ensure_ascii=False
+        )
+        call_info_list = [(name, parameters)]
+    elif "<function=" in text:  # llama3.1
+        action, _ = text.split("</function>")
+        parameters = action[action.find("{") :]
+        name = action.split("<function=")[1].split(">{")[0]
+        call_info_list = [(name, parameters)]
+    elif "<tool_call>" in text and "</tool_call>" in text:  # qwen2.5
+        # get tool_call in text
+        pattern = r"<tool_call>(.*?)</tool_call>"
+        match_result_list = re.findall(pattern, text, re.DOTALL)
+        call_info_list = []
+        for match_result in match_result_list:
+            action = json.loads(match_result)
+            call_info_list.append(
+                (action["name"], json.dumps(action["arguments"], ensure_ascii=False))
+            )
+        # get text outside of tags
+        if not text.startswith("<tool_call>"):
+            text = text[: text.find("<tool_call>")]
+        elif not text.endswith("</tool_call>"):
+            text = text[text.rfind("</tool_call>") + len("</tool_call>") :]
+        else:
+            text = ""
+    elif "<|python_tag|>" in text:  # llama3.2
+        _, action = text.split("<|python_tag|>")
+        action = json.loads(action)
+        name, parameters = action["name"], json.dumps(
+            action.get("parameters", action.get("arguments", {})), ensure_ascii=False
+        )
+        call_info_list = [(name, parameters)]
+    else:
+        raise RuntimeError(f"Unexpected model response: {text}")
+
+    call_info_list = [
+        (
+            [tool.function.name for tool in tools].index(call_info[0]),
+            call_info[0],
+            call_info[1],
+        )
+        for call_info in call_info_list
+    ]
+    return text, call_info_list

sglang/version.py

@@ -1 +1 @@
-__version__ = "0.4.1"
+__version__ = "0.4.1.post2"

{sglang-0.4.1.dist-info → sglang-0.4.1.post2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sglang
-Version: 0.4.1
+Version: 0.4.1.post2
 Summary: SGLang is yet another fast serving framework for large language models and vision language models.
 License:                                  Apache License
                                    Version 2.0, January 2004
@@ -243,7 +243,7 @@ Requires-Dist: torch; 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"
-Requires-Dist: sgl-kernel>=0.0.2.post8; extra == "srt"
+Requires-Dist: sgl-kernel>=0.0.2.post10; extra == "srt"
 Provides-Extra: srt-hip
 Requires-Dist: sglang[runtime_common]; extra == "srt-hip"
 Requires-Dist: torch; extra == "srt-hip"
@@ -351,15 +351,15 @@ The core features include:
 - [Backend: SGLang Runtime (SRT)](https://sgl-project.github.io/backend/backend.html)
 - [Frontend: Structured Generation Language (SGLang)](https://sgl-project.github.io/frontend/frontend.html)
 
-## Benchmark And Performance
+## 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/), [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, Meituan, NVIDIA, RunPod, Stanford, UC Berkeley, xAI, 01.AI and DataCrunch.
+The project is supported by (alphabetically): AMD, Baseten, DataCrunch, Etched, Hyperbolic, Jam & Tea Studios, LinkedIn, LMSYS.org, Meituan, NVIDIA, RunPod, Stanford, UC Berkeley, UCLA, xAI, 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).
-Please cite our paper, [SGLang: Efficient Execution of Structured Language Model Programs](https://arxiv.org/abs/2312.07104), if you find the project useful.
+Please cite the paper, [SGLang: Efficient Execution of Structured Language Model Programs](https://arxiv.org/abs/2312.07104), if you find the project useful.

{sglang-0.4.1.dist-info → sglang-0.4.1.post2.dist-info}/RECORD

@@ -1,17 +1,17 @@
 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=iQiJCK3KQDCdwU1NVbIwbtthssWzBXiIsKUDA7Z_hO0,12510
+sglang/bench_offline_throughput.py,sha256=r-uBvpnx-30mAnVwQB4WlqiXxy2fn5a1NUARwZcaIo4,12533
 sglang/bench_one_batch.py,sha256=jkyMhK0lqn5dRCYgAh30qZrNHP4gAbXODymBMNXK86I,15859
 sglang/bench_one_batch_server.py,sha256=-fV9FTLNNcSIy0pgYeggXedPVK0fVsXZqVQswT8OMOY,5945
-sglang/bench_serving.py,sha256=3VQatM51v9f55aUQQ5crYMxxKHr1AbThicsWfBy_tjU,53190
+sglang/bench_serving.py,sha256=YQiCZreejCPBTqMmZsCB99RMi1N-Jx-dZtaafcQ8-14,53377
 sglang/check_env.py,sha256=4OqpZaEJOfBM6-vtPILto5kqDmgiZM1Koc7lK78A7CI,8427
 sglang/global_config.py,sha256=fnT0U9vlHdGaQFKN9tYTnUF4-eVW4HYQURd5zvPtrg0,1286
 sglang/launch_server.py,sha256=4y2QeSj0wVNB9MJQZeahD4ahTDU6gwqo7MPUytyFop0,403
 sglang/launch_server_llavavid.py,sha256=tGc17S1vUfLwbi1GB26oOdXxTWr7gjlqpTrPnrMRNO8,1007
 sglang/llama3_eval.py,sha256=gWSboDchIGybIce88bJlrCG0yiLZ513mw4gcutJlzGM,10017
 sglang/utils.py,sha256=23jf4Mz8E5p5a6JOkjnfYZixdjZUk88F_mZ8rZcby5Q,11597
-sglang/version.py,sha256=pMtTmSUht-XtbR_7Doz6bsQqopJJd8rZ8I8zy2HwwoA,22
+sglang/version.py,sha256=1g4t88smWYt1DD5SJZdzXI13OPbsQPOEMX9twA4wq6A,28
 sglang/lang/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sglang/lang/chat_template.py,sha256=cnfjjxIIcYRGRxXlJlOGnpFxFuhMHut7DS52LsOMKcA,15826
 sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
@@ -23,7 +23,7 @@ sglang/lang/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSu
 sglang/lang/backend/anthropic.py,sha256=EXRX7xJgA5KZszX7toSLVnKzFQ5EO0Loj-YjHFtxSxg,2081
 sglang/lang/backend/base_backend.py,sha256=tdoh9YF3CyekY1BKiX9n7-aA4srDWIuA4RDJLM7q8qg,1985
 sglang/lang/backend/litellm.py,sha256=ugmL7sfUxkUHVbHtwNzHgdQAEd4UCjNQboFuE3KThcY,2450
-sglang/lang/backend/openai.py,sha256=qM7eVH_kMxnDd2rpxOH0v76KxtOJFlAwgLgWIKvFGCI,15060
+sglang/lang/backend/openai.py,sha256=ha9a2P6T80TmSgYlyIwB1qYawWkjcOgiOptkktkqa1U,15436
 sglang/lang/backend/runtime_endpoint.py,sha256=dfs-yZ1ekKmnbpZLluQHWPmMeZJKbaaZRRGYRa9eBE8,10541
 sglang/lang/backend/vertexai.py,sha256=O-iBLD-y3vq80UxnrAoJri7bxpgd-_eakZ88Cf8bEGA,4855
 sglang/srt/_custom_ops.py,sha256=Y4gyTDGhWz-W2Igq25Ojm8XFiyvkawW9I-79iwYvxJ0,3574
@@ -32,20 +32,20 @@ sglang/srt/conversation.py,sha256=u9zFU8aMYzwHUbQRKU76B_T-jfLlPoxUcWG_nRbDM2I,21
 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=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
-sglang/srt/server.py,sha256=E9YKKXpXv3vPvRy0-cgcy0-5UA-OZz42-32EZWKTicA,34661
-sglang/srt/server_args.py,sha256=LgnQ-kBJZ3E7hMMZj9bSK0mn7Bhjk1nJHxLcxl-lGTM,34572
-sglang/srt/utils.py,sha256=J8kFl6kDBwFZCM6AKaVTiqdhJKRg0JOH0pNrD1ZeWmM,41726
+sglang/srt/server.py,sha256=sDERAZlRa6OTaUk-SfW5aKJbPui1COpPG34HDlMHMNc,34916
+sglang/srt/server_args.py,sha256=lBMOME7OSqG0Opinsin-QsioNrWpp2M0ZosB8cXoRrY,33917
+sglang/srt/utils.py,sha256=i8MjcaSQjPPfPZ0txufTtqLr4Q7YhHQ86L1i9j-y5yY,44131
 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
 sglang/srt/configs/load_config.py,sha256=TcPi_HY6xu5SiVZsxPOoB5pGeDUNebOk7muoUH9VBDg,3083
-sglang/srt/configs/model_config.py,sha256=vVarlLTw9Ged1PXIwRP-R8UhiG6oaezNIZhTNuF0eQc,16070
+sglang/srt/configs/model_config.py,sha256=QP_6WaWMrE4NNF-XODRomiQPO0FABmVZIj5A-qJfnYg,16427
 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=CipNHNNXs8xtnJNVNe6FCwZUlSbIXbGmWVlZz3hUpFQ,6820
 sglang/srt/constrained/outlines_jump_forward.py,sha256=iZWXeR3gNYoMubLGyFmLPO4V2YsN5DiGjD71Xk9iFaE,6418
-sglang/srt/constrained/xgrammar_backend.py,sha256=4It9_GqU4UZFhxIw_7hkzpXaMPUtksk6Xfe0Agsfw7A,4620
+sglang/srt/constrained/xgrammar_backend.py,sha256=76oUFXeB29bfnEVWa1-rIrwQm5jhuMlzAX10HtAq1fQ,4887
 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
@@ -63,49 +63,49 @@ sglang/srt/layers/activation.py,sha256=EboMjT9HV2tNHQ6rzpojtlkzev1lAFbhQlxMg9hwx
 sglang/srt/layers/custom_op_util.py,sha256=0vu-yX2wwonmO1L_o5G7SA6C-8XuhDIh9rPDvNeLhoc,922
 sglang/srt/layers/layernorm.py,sha256=nRQ1w1xSUcU-zlqVC61BnGG6otS5W1w9VaSzeXizrx4,4037
 sglang/srt/layers/linear.py,sha256=KyRFU0VcoNuN-hnQB9QQcBN9NCpeqPtLzzufIHUpV6w,47064
-sglang/srt/layers/logits_processor.py,sha256=JlOU0x8vBGIuTwHSdjR6Kly9_uzilBMv0NE_rvUx0W4,14747
+sglang/srt/layers/logits_processor.py,sha256=Imh-qY1D9J80DZVSVV0LfTiHMEw6oQ3JbY9lXxPZAXE,15656
 sglang/srt/layers/pooler.py,sha256=rj2lygvleBnyLCBZ8I11HGMgpfIDsT0l3PIkshJwdu4,1606
 sglang/srt/layers/radix_attention.py,sha256=E4cmvkcCdCtb6VyLNrCKy1D6VwHQ063oH3JQXPaRy6w,2178
 sglang/srt/layers/rotary_embedding.py,sha256=29tx3JNR40AoXqBa2cFGBjva9vU2xgFipETlpMaaZas,3985
 sglang/srt/layers/sampler.py,sha256=k4Op_HMkQfT7t9wgQwBVotfTUXEocrzRyQqEFnff1pc,5511
 sglang/srt/layers/torchao_utils.py,sha256=dQVuWNXxAvOPjr2G5BBMWqC2oKcS2B52rx-fEc_elmc,3545
 sglang/srt/layers/vocab_parallel_embedding.py,sha256=slGwLiWjuFLCUdRe-GTlfumyZpqVX9VF6No_UGOT-hA,21624
-sglang/srt/layers/attention/__init__.py,sha256=KIJhzOJWYioQE7Va4D83-V-ZUZVMZcczuNgDC3dlSRo,2583
+sglang/srt/layers/attention/__init__.py,sha256=lNLfWqePc5NMej-AcXl97vxVXsxQOgP7dNNb2ibyUWI,2562
 sglang/srt/layers/attention/double_sparsity_backend.py,sha256=RQdEKRykSLf9ilnaHmR6T7RFqh4emH_adfB3aJN2BUU,10920
-sglang/srt/layers/attention/flashinfer_backend.py,sha256=umD1E2zvMnPbbgvx2Ex5LQB6a4a41brjsks1M0gFMMU,26357
+sglang/srt/layers/attention/flashinfer_backend.py,sha256=8nH4EIEXvNk9yZVl7mSn78w5Dli5UiWL-ZCeYykG9HI,27280
 sglang/srt/layers/attention/torch_native_backend.py,sha256=nQdeqWEMMH_wrod5wssDCJG-uPKm0uslvkALKqPRPQ8,10509
 sglang/srt/layers/attention/triton_backend.py,sha256=-TobyZHwlbJ5HhbFg-jgCqVOw4Y-opgEuFo-EusASQc,6264
 sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=oJ_UK1t229zF3hbTDiQe7t-X-IbM2dOxx4U2ch-vmjA,17847
 sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=1pSXfY3EEaM7iRN_uElHnAfsrJMhTFbu9fj8Z0O2PbE,21480
-sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=tZJhzqcf1KKMT8z7_32eVk_D1NHP71c-S3UNxemfAHM,11542
+sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=DWOZXSTVN5ZbcFjDjcqs-nPdUkxSwum0SVXhVKqwh2g,11688
 sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=lojFXRZMLWkzS2Y8uxaolnQhXaWKG19mCAWaF5KQeiI,6087
 sglang/srt/layers/moe/fused_moe_native.py,sha256=8q-LFZMSCGLc2_Gltp2lH0gSb4A1WOuKQW3wo3rpj5g,1601
-sglang/srt/layers/moe/topk.py,sha256=YjIiFqMERvkChkwZUqTrL_xaQyzsYsZzVUe4PzAhRZI,6299
+sglang/srt/layers/moe/topk.py,sha256=JpeIl_-CNk0yyG3k5fmmNbbmR2_9bkKC23UoLOlMkjw,6954
 sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sglang/srt/layers/moe/ep_moe/kernels.py,sha256=wb_S2qLxoWWgQu9coXy0XLNGvHzdZSdwXr0PGy4QySg,10940
 sglang/srt/layers/moe/ep_moe/layer.py,sha256=6iQU5ZjQ8IXGoQ8ZlBuJqyQxYTEem9vXI6rbVIWKlZw,22303
 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=GVugCKapd3CvgkvPQ_FmQplC12-grv3n1FRkLJc6WhY,30790
+sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=KvOy544x_4nRqg50o5YHQpHvF8TUD7q9LXDAWPGJlAA,31796
 sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=BclDj5JyCy-8Bfue4broL1-IG6a4dUyggE9WQLa06sg,20575
 sglang/srt/layers/quantization/__init__.py,sha256=VPYXShHvbvkOgVBlkIqic4RhdJ1y6EZ3r34T-nZMT1k,4606
 sglang/srt/layers/quantization/base_config.py,sha256=daK9p0aijMszLUm1W4Pc33FK87MdqYK1NoWFKif-j80,4599
-sglang/srt/layers/quantization/fp8.py,sha256=wNnpXLroIl7D98mlfCiXZPE9hrP5ricHrXY1WZBzEEo,30810
-sglang/srt/layers/quantization/fp8_kernel.py,sha256=v4-7hCQFyuUSZmeJS_5VDCu6a1-EGWXQ088FdPTjO_0,8137
-sglang/srt/layers/quantization/fp8_utils.py,sha256=HBJBaNcln1NrLxzw0ppUjMd6w-ryuGDDHCYJq7mRQac,4035
+sglang/srt/layers/quantization/fp8.py,sha256=k4mw-iKxlaEWRkGgaoxCLzZ_dYydyRj0y1N1B_umMwU,32668
+sglang/srt/layers/quantization/fp8_kernel.py,sha256=cYF4ckqrUyhCO9Ha7zi05R8EhRaqSa8rFpYisz-9Ed0,10743
+sglang/srt/layers/quantization/fp8_utils.py,sha256=qBVJXxbxqmf8-Juq0t-IXWjlaZoePJqFNYcs9-oT5Yo,4150
 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
 sglang/srt/managers/data_parallel_controller.py,sha256=psI4FAuBGjtdnEuwagnGdtRqvqSSxOROfNKQqVDqlVA,8382
 sglang/srt/managers/detokenizer_manager.py,sha256=nZkbwt4yty_oy8rvg4T7PbgyVLoBLohvHl25xlQpBoo,8439
 sglang/srt/managers/image_processor.py,sha256=Y8RgyrzbJjJTpjbnZDa5qiiG5wWjZ68rOXUPDi6kkFo,13698
-sglang/srt/managers/io_struct.py,sha256=_LWWqT3LNwZGaWhg2d3kTg1V2MTHKzRasCvxF9Nfpi4,15429
-sglang/srt/managers/schedule_batch.py,sha256=qryPWCdOTFzxomDa80U-5guShOb1K4kBUWcPCCchYB8,45762
-sglang/srt/managers/schedule_policy.py,sha256=cLNi__smbg02keWgUMfB_nEM3vllocPB0XyG1P5qO7I,15469
-sglang/srt/managers/scheduler.py,sha256=3Olw4Yf4Qtn1i4PqK3PT9hkXYGE8nemL2_Xjn8JLxAQ,61819
-sglang/srt/managers/session_controller.py,sha256=Yp-IV3rXczACZxZXmF-QxW9CWICGy8KHQ9ttBGJ8WXA,2800
-sglang/srt/managers/tokenizer_manager.py,sha256=Vta7Lysvh4rPWqEB00shqAzpGUfv7GdPETDqFCU8RxA,31556
-sglang/srt/managers/tp_worker.py,sha256=X1EwFX3FSsmXx7jeeX2tjZRocaujabQYWm-M-0CFEBE,7363
-sglang/srt/managers/tp_worker_overlap_thread.py,sha256=-QNBJRKxraa9Xt2WI1AFzZYdneIJ1eXv0GjFzDqXoE0,8926
+sglang/srt/managers/io_struct.py,sha256=Gru7LEyc3tcM_LewoteCb7GXIrh-OYhA2CnEvjc1Cis,15769
+sglang/srt/managers/schedule_batch.py,sha256=KnoVuWgINnyard-BOXCo0jm3IMdXN9wIwnftMKcag-s,46097
+sglang/srt/managers/schedule_policy.py,sha256=QxjQ8-le062AMHHxool6CxkhvB4FIwhOQPzTX_JwL6U,15447
+sglang/srt/managers/scheduler.py,sha256=Z1_wf6OCC8Hevc7y0D4Rt4EW5Et9bgTL9oJOkmNmDjo,63490
+sglang/srt/managers/session_controller.py,sha256=3laMRIXEYWDjfytCjPs0vw_Tw__k-nKBY-bYzycYbfc,5482
+sglang/srt/managers/tokenizer_manager.py,sha256=SXvVZHFMBCtcLkKnq-O3uzwrEhfVqk6Y1fzeBEFNq0E,33010
+sglang/srt/managers/tp_worker.py,sha256=8RVBLQaS3TnX7Z4J35RVrFN0M6PVnRBhct3sczBL4dY,7644
+sglang/srt/managers/tp_worker_overlap_thread.py,sha256=JQfrVPeE56ZGJ3nozkhZR-RSb2oePsY7iuedM7XCtdQ,9157
 sglang/srt/mem_cache/base_prefix_cache.py,sha256=QC8HS8RC5DXu14kyXsxAgEUsn0f932p2DjqzbKjc6Bs,962
 sglang/srt/mem_cache/chunk_cache.py,sha256=R2gHAuqKd5ayQW3NnsgoGUH31---Z5izCDyCqLL0FjQ,2524
 sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
@@ -114,10 +114,10 @@ sglang/srt/mem_cache/radix_cache.py,sha256=c5voySV5L855c0G9cBEc9iQ4nR7PDDmg0V6fW
 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=1n5WxoE9-0B3unwkkcR355K_D290h2LGt_7EvH02DQM,16246
-sglang/srt/model_executor/forward_batch_info.py,sha256=L5mVoW5SaO6To-7nGk0TZM-FFB5_78cARpJ-aC2rwD0,12883
-sglang/srt/model_executor/model_runner.py,sha256=Bm3NWTS3xmOGXEJnucnJZQldpVOzu-DCEUfaJy_PTU0,30104
+sglang/srt/model_executor/forward_batch_info.py,sha256=vqF8XrHQPk3ZL7HqPvvkfP53oqBx0Fajb5lAIkdifBo,13961
+sglang/srt/model_executor/model_runner.py,sha256=TjvAwwr7EqZdmE-5HbuQMeEa0e0FqY6LeqqzEAHXMPU,30012
 sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
-sglang/srt/model_loader/loader.py,sha256=VBrY4W9CiVvS_D8yXhdkW9jReV9rSMSkJplabz0Fxgk,43528
+sglang/srt/model_loader/loader.py,sha256=7OG_8-66vFDFZ9kVKGNK1BFBjZ6ql449dlyvdCbMqvE,43876
 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
@@ -128,7 +128,7 @@ sglang/srt/models/deepseek.py,sha256=_cVOvR6eSEgRf6TUBpTD5uMdijDWFw4sSt4lGzl8tbg
 sglang/srt/models/deepseek_v2.py,sha256=-v_OJr2c3gJ0NMxQjvT3Jknz1XPGkzKx0TVR3NIiC6A,37284
 sglang/srt/models/exaone.py,sha256=dkERTZVxrRroqu5AGLP7D4N6n8HvDqlNaDQUIe15mZY,13038
 sglang/srt/models/gemma.py,sha256=ydRqsG-7004r1fAiz01LHUmcj_6XN0Tn4xO1keJnMQk,12126
-sglang/srt/models/gemma2.py,sha256=41PlW8pMb4rMETdAni_JWDhZeIn_QsTQireAyUjsURA,15848
+sglang/srt/models/gemma2.py,sha256=-bFN-Te3YWAunLCrF-XFk_6fJS7gHM4Ca6h6aesXUTM,16362
 sglang/srt/models/gemma2_reward.py,sha256=nJ01KfqLSJtqMLm3sG8p2mGZFK1xhhjh7I7Ccb-_Hq8,2494
 sglang/srt/models/gpt2.py,sha256=2je1kE09sGcaORWnJuGYAkcwwOrT9EK-KhQaoCKjCSA,9517
 sglang/srt/models/gpt_bigcode.py,sha256=tovyOdJu2x3LkzmkdFXX_iJdkxuyChIDxwgvPBy6UPo,9528
@@ -136,8 +136,9 @@ sglang/srt/models/granite.py,sha256=AeQY9Dxd1ZnwgCYBK0vSXXiMGM-yt9iaOVf_ruOUHXw,
 sglang/srt/models/grok.py,sha256=J9lgNbFebvXgF19nfZyHwlGPlGWY_m0LgP506YvOYrU,15668
 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=S7nS05hhFGghXu0v-w9RZyBTY6OCEVF5Aaw4GX_E_9g,19929
+sglang/srt/models/llama.py,sha256=4UPKF7erp7qqBD11uvvQkO1Fo_wDs71BmA8Y2csXRcA,20302
 sglang/srt/models/llama_classification.py,sha256=DwboM1xHXdf3Fddf7xGnrfdOLJwXdiJs994cIpAPa2g,2984
+sglang/srt/models/llama_eagle.py,sha256=88DzR54DKBIKJ1h-bkIa8mc1qJnlkdZ1eGYY3c5mpBY,4442
 sglang/srt/models/llama_embedding.py,sha256=rh-AiczPY_pTpzcACHvSMVjh1hsV_MZBBwP0LQxPsGM,3130
 sglang/srt/models/llama_reward.py,sha256=oPxh5E2UkxLULNdR68dFvt2I7j33CJFN6nyA-8L2_cg,4516
 sglang/srt/models/llava.py,sha256=xrkg8sht8tBOID7427IEZtHL-KKWfEivDe2NqGjTSAs,26373
@@ -162,16 +163,17 @@ sglang/srt/models/torch_native_llama.py,sha256=YeXHorFm6QfnczLXwPb5TG9a-He0uiA9R
 sglang/srt/models/xverse.py,sha256=Oq--KqvbYu2H4TMVGEHpSnJLEwXBpxlncR9ilsQeckc,13579
 sglang/srt/models/xverse_moe.py,sha256=7E60YIST4ELYwLRgjtHiLRI5Uyc7XqQTM7jQXiWaQs4,15541
 sglang/srt/models/yivl.py,sha256=88OubtuZ38Dxb2LzfV_MTPBI4wKhh4NJqFu--efbhFM,4809
-sglang/srt/openai_api/adapter.py,sha256=DbLA4-v-QrKJHYDH4fpDSXqmyz_vpcFE-1tnhh60m6o,54057
-sglang/srt/openai_api/protocol.py,sha256=ecRNNqkhwwKZaIoJlPhtp2VTcHxBJDbNN8lrKS7uBx8,10406
+sglang/srt/openai_api/adapter.py,sha256=HvgeFPWv-v8LOiYF2iNCo-14BIZLAPznNTCUbubB2Rg,57091
+sglang/srt/openai_api/protocol.py,sha256=anWGr2Br8gVYm6Z0yvDwjXLaPCPuvJZ28gr5rV2dhVQ,11613
 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/sampling_params.py,sha256=BkgCJAOSmQXwJrNXg26zSjKfMy0d5mMN6oHRk_ZuESI,5499
 sglang/srt/sampling/penaltylib/__init__.py,sha256=5vQw0Y5DSzmsoFg1IdMIKLwFVhYZ5ArADHVBYbSmOec,513
 sglang/srt/sampling/penaltylib/orchestrator.py,sha256=J-DEemZcKm1--o37kf3qDOE8SZ_6H3d5oex49Mgq2ZU,10762
 sglang/srt/sampling/penaltylib/penalizers/frequency_penalty.py,sha256=1Zp2aL6dD60mwD1tCcSG0x5IYo0v4z9ce-q_YwbJ9f8,2490
 sglang/srt/sampling/penaltylib/penalizers/min_new_tokens.py,sha256=_Nxv0XgUPirZjw2SEJYp_Cd9ZcLwmt7h6JE6J4hhFq4,3629
 sglang/srt/sampling/penaltylib/penalizers/presence_penalty.py,sha256=5tOgCg7OvE9kSN9VMCpH1hwqo1YMxt9iS5PVpct9HpU,2468
 sglang/srt/sampling/penaltylib/penalizers/repetition_penalty.py,sha256=m22Rfn1RuB1HpImBDECsiJ2VooBYpsFADAwnk1EPzk0,2751
+sglang/srt/speculative/spec_info.py,sha256=d-82uWEC-QBqAgv3XGDNDW8DlHv4MtUsZghFqzGwV7U,352
 sglang/test/few_shot_gsm8k.py,sha256=7yDbEQe49gZeJhz2wFFX-gf_59ThDKsCS1xwfogNc7k,4034
 sglang/test/few_shot_gsm8k_engine.py,sha256=QQbrwOX6-cJDD3RZC_e7zPnt6aSo8JdF8X_lRHSjdDM,3886
 sglang/test/run_eval.py,sha256=9yO0hXZOcn4abEOs96T-XPguDEklK16Ltco0pGF3zCg,4020
@@ -188,8 +190,8 @@ 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=HJG7kUQOk6n9FBbH89PDtQ41C3kt1cfJODhAEcFT0AQ,23823
 sglang/test/srt/sampling/penaltylib/utils.py,sha256=CjxHgywh0hx_87iynzQt_ztHu6zBVuE-YrZ-XPmW6U4,12906
-sglang-0.4.1.dist-info/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
-sglang-0.4.1.dist-info/METADATA,sha256=RlVEQtwr_CCGTs83vNPwWXQukutbFfBz9xBPlXSl6qc,22523
-sglang-0.4.1.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-sglang-0.4.1.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
-sglang-0.4.1.dist-info/RECORD,,
+sglang-0.4.1.post2.dist-info/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
+sglang-0.4.1.post2.dist-info/METADATA,sha256=eORQMKMQDt_eTOh6PxMzIvyjNbg2FllxXss2Z9jU3Ug,22544
+sglang-0.4.1.post2.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+sglang-0.4.1.post2.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
+sglang-0.4.1.post2.dist-info/RECORD,,