sglang 0.3.5.post2__py3-none-any.whl → 0.3.6.post1__py3-none-any.whl

sglang/test/test_utils.py

@@ -2,6 +2,7 @@
 
 import argparse
 import asyncio
+import copy
 import os
 import random
 import subprocess
@@ -43,7 +44,7 @@ DEFAULT_MODEL_NAME_FOR_NIGHTLY_EVAL_QUANT_TP1 = "hugging-quants/Meta-Llama-3.1-8
 
 def is_in_ci():
     """Return whether it is in CI runner."""
-    return os.getenv("SGLANG_IS_IN_CI", "false") == "true"
+    return os.getenv("SGLANG_IS_IN_CI", "false").lower() == "true"
 
 
 if is_in_ci():
@@ -438,18 +439,22 @@ def popen_launch_server(
         process = subprocess.Popen(command, stdout=None, stderr=None, env=env)
 
     start_time = time.time()
-    while time.time() - start_time < timeout:
-        try:
-            headers = {
-                "Content-Type": "application/json; charset=utf-8",
-                "Authorization": f"Bearer {api_key}",
-            }
-            response = requests.get(f"{base_url}/health_generate", headers=headers)
-            if response.status_code == 200:
-                return process
-        except requests.RequestException:
-            pass
-        time.sleep(10)
+    with requests.Session() as session:
+        while time.time() - start_time < timeout:
+            try:
+                headers = {
+                    "Content-Type": "application/json; charset=utf-8",
+                    "Authorization": f"Bearer {api_key}",
+                }
+                response = session.get(
+                    f"{base_url}/health_generate",
+                    headers=headers,
+                )
+                if response.status_code == 200:
+                    return process
+            except requests.RequestException:
+                pass
+            time.sleep(10)
     raise TimeoutError("Server failed to start within the timeout period.")
 
 
@@ -529,6 +534,7 @@ def run_bench_serving(
     random_input_len=4096,
     random_output_len=2048,
     disable_stream=False,
+    need_warmup=False,
 ):
     # Launch the server
     base_url = DEFAULT_URL_FOR_TEST
@@ -562,9 +568,14 @@ def run_bench_serving(
         disable_stream=disable_stream,
         disable_ignore_eos=False,
         extra_request_body=None,
+        profile=None,
     )
 
     try:
+        if need_warmup:
+            warmup_args = copy.deepcopy(args)
+            warmup_args.num_prompts = 16
+            run_benchmark(warmup_args)
         res = run_benchmark(args)
     finally:
         kill_child_process(process.pid, include_self=True)
@@ -573,11 +584,11 @@ def run_bench_serving(
     return res
 
 
-def run_bench_latency(model, other_args):
+def run_bench_one_batch(model, other_args):
     command = [
         "python3",
         "-m",
-        "sglang.bench_latency",
+        "sglang.bench_one_batch",
         "--model-path",
         model,
         "--batch-size",
@@ -664,7 +675,7 @@ def run_and_check_memory_leak(
     workload_func,
     disable_radix_cache,
     enable_mixed_chunk,
-    enable_overlap,
+    disable_overlap,
     chunked_prefill_size,
 ):
     other_args = ["--chunked-prefill-size", str(chunked_prefill_size)]
@@ -672,8 +683,8 @@ def run_and_check_memory_leak(
         other_args += ["--disable-radix-cache"]
     if enable_mixed_chunk:
         other_args += ["--enable-mixed-chunk"]
-    if enable_overlap:
-        other_args += ["--enable-overlap-schedule"]
+    if disable_overlap:
+        other_args += ["--disable-overlap-schedule"]
 
     model = DEFAULT_MODEL_NAME_FOR_TEST
     port = random.randint(4000, 5000)
@@ -725,7 +736,7 @@ def run_and_check_memory_leak(
 def run_mmlu_test(
     disable_radix_cache=False,
     enable_mixed_chunk=False,
-    enable_overlap=False,
+    disable_overlap=False,
     chunked_prefill_size=32,
 ):
     def workload_func(base_url, model):
@@ -748,7 +759,7 @@ def run_mmlu_test(
         workload_func,
         disable_radix_cache,
         enable_mixed_chunk,
-        enable_overlap,
+        disable_overlap,
         chunked_prefill_size,
     )
 

sglang/version.py

@@ -1 +1 @@
-__version__ = "0.3.5.post2"
+__version__ = "0.3.6.post1"

{sglang-0.3.5.post2.dist-info → sglang-0.3.6.post1.dist-info}/LICENSE

@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright [yyyy] [name of copyright owner]
+   Copyright 2023-2024 SGLang Team
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

{sglang-0.3.5.post2.dist-info → sglang-0.3.6.post1.dist-info}/METADATA

@@ -1,8 +1,8 @@
 Metadata-Version: 2.1
 Name: sglang
-Version: 0.3.5.post2
+Version: 0.3.6.post1
 Summary: SGLang is yet another fast serving framework for large language models and vision language models.
-License: Apache License
+License:                                  Apache License
                                    Version 2.0, January 2004
                                 http://www.apache.org/licenses/
         
@@ -190,7 +190,7 @@ License: Apache License
               same "printed page" as the copyright notice for easier
               identification within third-party archives.
         
-           Copyright [yyyy] [name of copyright owner]
+           Copyright 2023-2024 SGLang Team
         
            Licensed under the Apache License, Version 2.0 (the "License");
            you may not use this file except in compliance with the License.
@@ -215,74 +215,85 @@ Requires-Dist: requests
 Requires-Dist: tqdm
 Requires-Dist: numpy
 Requires-Dist: IPython
-Provides-Extra: all
-Requires-Dist: sglang[srt]; extra == "all"
-Requires-Dist: sglang[openai]; extra == "all"
-Requires-Dist: sglang[anthropic]; extra == "all"
-Requires-Dist: sglang[litellm]; extra == "all"
-Provides-Extra: all_hip
-Requires-Dist: sglang[srt_hip]; extra == "all-hip"
-Requires-Dist: sglang[openai]; extra == "all-hip"
-Requires-Dist: sglang[anthropic]; extra == "all-hip"
-Requires-Dist: sglang[litellm]; extra == "all-hip"
-Provides-Extra: all_xpu
-Requires-Dist: sglang[srt_xpu]; extra == "all-xpu"
-Requires-Dist: sglang[openai]; extra == "all-xpu"
-Requires-Dist: sglang[anthropic]; extra == "all-xpu"
-Requires-Dist: sglang[litellm]; extra == "all-xpu"
-Provides-Extra: anthropic
-Requires-Dist: anthropic>=0.20.0; extra == "anthropic"
-Provides-Extra: dev
-Requires-Dist: sglang[all]; extra == "dev"
-Requires-Dist: sglang[test]; extra == "dev"
-Provides-Extra: dev_hip
-Requires-Dist: sglang[all_hip]; extra == "dev-hip"
-Requires-Dist: sglang[test]; extra == "dev-hip"
-Provides-Extra: dev_xpu
-Requires-Dist: sglang[all_xpu]; extra == "dev-xpu"
-Requires-Dist: sglang[test]; extra == "dev-xpu"
-Provides-Extra: litellm
-Requires-Dist: litellm>=1.0.0; extra == "litellm"
-Provides-Extra: openai
-Requires-Dist: openai>=1.0; extra == "openai"
-Requires-Dist: tiktoken; extra == "openai"
-Provides-Extra: runtime_common
+Provides-Extra: runtime-common
 Requires-Dist: aiohttp; extra == "runtime-common"
 Requires-Dist: decord; extra == "runtime-common"
 Requires-Dist: fastapi; extra == "runtime-common"
-Requires-Dist: hf-transfer; extra == "runtime-common"
-Requires-Dist: huggingface-hub; extra == "runtime-common"
+Requires-Dist: hf_transfer; extra == "runtime-common"
+Requires-Dist: huggingface_hub; extra == "runtime-common"
 Requires-Dist: interegular; extra == "runtime-common"
+Requires-Dist: modelscope; extra == "runtime-common"
 Requires-Dist: orjson; extra == "runtime-common"
+Requires-Dist: outlines<0.1.0,>=0.0.44; extra == "runtime-common"
 Requires-Dist: packaging; extra == "runtime-common"
 Requires-Dist: pillow; extra == "runtime-common"
 Requires-Dist: prometheus-client>=0.20.0; extra == "runtime-common"
 Requires-Dist: psutil; extra == "runtime-common"
 Requires-Dist: pydantic; extra == "runtime-common"
 Requires-Dist: python-multipart; extra == "runtime-common"
+Requires-Dist: pyzmq>=25.1.2; extra == "runtime-common"
 Requires-Dist: torchao; extra == "runtime-common"
 Requires-Dist: uvicorn; extra == "runtime-common"
 Requires-Dist: uvloop; extra == "runtime-common"
-Requires-Dist: pyzmq>=25.1.2; extra == "runtime-common"
-Requires-Dist: outlines<0.1.0,>=0.0.44; extra == "runtime-common"
-Requires-Dist: modelscope; extra == "runtime-common"
+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"
-Provides-Extra: srt_hip
+Requires-Dist: vllm>=0.6.3.post1; extra == "srt"
+Provides-Extra: srt-hip
 Requires-Dist: sglang[runtime_common]; extra == "srt-hip"
 Requires-Dist: torch; extra == "srt-hip"
 Requires-Dist: vllm==0.6.3.dev13; extra == "srt-hip"
-Provides-Extra: srt_xpu
+Provides-Extra: srt-xpu
 Requires-Dist: sglang[runtime_common]; extra == "srt-xpu"
+Provides-Extra: srt-hpu
+Requires-Dist: sglang[runtime_common]; extra == "srt-hpu"
+Provides-Extra: openai
+Requires-Dist: openai>=1.0; extra == "openai"
+Requires-Dist: tiktoken; extra == "openai"
+Provides-Extra: anthropic
+Requires-Dist: anthropic>=0.20.0; extra == "anthropic"
+Provides-Extra: litellm
+Requires-Dist: litellm>=1.0.0; extra == "litellm"
 Provides-Extra: test
 Requires-Dist: jsonlines; extra == "test"
 Requires-Dist: matplotlib; extra == "test"
 Requires-Dist: pandas; extra == "test"
-Requires-Dist: sentence-transformers; extra == "test"
+Requires-Dist: sentence_transformers; extra == "test"
 Requires-Dist: accelerate; extra == "test"
 Requires-Dist: peft; extra == "test"
+Provides-Extra: all
+Requires-Dist: sglang[srt]; extra == "all"
+Requires-Dist: sglang[openai]; extra == "all"
+Requires-Dist: sglang[anthropic]; extra == "all"
+Requires-Dist: sglang[litellm]; extra == "all"
+Provides-Extra: all-hip
+Requires-Dist: sglang[srt_hip]; extra == "all-hip"
+Requires-Dist: sglang[openai]; extra == "all-hip"
+Requires-Dist: sglang[anthropic]; extra == "all-hip"
+Requires-Dist: sglang[litellm]; extra == "all-hip"
+Provides-Extra: all-xpu
+Requires-Dist: sglang[srt_xpu]; extra == "all-xpu"
+Requires-Dist: sglang[openai]; extra == "all-xpu"
+Requires-Dist: sglang[anthropic]; extra == "all-xpu"
+Requires-Dist: sglang[litellm]; extra == "all-xpu"
+Provides-Extra: all-hpu
+Requires-Dist: sglang[srt_hpu]; extra == "all-hpu"
+Requires-Dist: sglang[openai]; extra == "all-hpu"
+Requires-Dist: sglang[anthropic]; extra == "all-hpu"
+Requires-Dist: sglang[litellm]; extra == "all-hpu"
+Provides-Extra: dev
+Requires-Dist: sglang[all]; extra == "dev"
+Requires-Dist: sglang[test]; extra == "dev"
+Provides-Extra: dev-hip
+Requires-Dist: sglang[all_hip]; extra == "dev-hip"
+Requires-Dist: sglang[test]; extra == "dev-hip"
+Provides-Extra: dev-xpu
+Requires-Dist: sglang[all_xpu]; extra == "dev-xpu"
+Requires-Dist: sglang[test]; extra == "dev-xpu"
+Provides-Extra: dev-hpu
+Requires-Dist: sglang[all_hpu]; extra == "dev-hpu"
+Requires-Dist: sglang[test]; extra == "dev-hpu"
 
 <div align="center"  id="sglangtop">
 <img src="https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png" alt="logo" width="400" margin="10px"></img>
@@ -321,21 +332,16 @@ SGLang is a fast serving framework for large language models and vision language
 It makes your interaction with models faster and more controllable by co-designing the backend runtime and frontend language.
 The core features include:
 
-- **Fast Backend Runtime**: Provides efficient serving with RadixAttention for prefix caching, jump-forward constrained decoding, continuous batching, token attention (paged attention), tensor parallelism, FlashInfer kernels, chunked prefill, and quantization (INT4/FP8/AWQ/GPTQ).
+- **Fast Backend Runtime**: Provides efficient serving with RadixAttention for prefix caching, jump-forward constrained decoding, overhead-free CPU scheduler, continuous batching, token attention (paged attention), tensor parallelism, FlashInfer kernels, chunked prefill, and quantization (FP8/INT4/AWQ/GPTQ).
 - **Flexible Frontend Language**: Offers an intuitive interface for programming LLM applications, including chained generation calls, advanced prompting, control flow, multi-modal inputs, parallelism, and external interactions.
-- **Extensive Model Support**: Supports a wide range of generative models (Llama, Gemma, Mistral, QWen, DeepSeek, LLaVA, etc.), embedding models (e5-mistral, gte) and reward models (Skywork), with easy extensibility for integrating new models.
+- **Extensive Model Support**: Supports a wide range of generative models (Llama, Gemma, Mistral, QWen, DeepSeek, LLaVA, etc.), embedding models (e5-mistral, gte, mcdse) and reward models (Skywork), with easy extensibility for integrating new models.
 - **Active Community**: SGLang is open-source and backed by an active community with industry adoption.
 
 ## Getting Started
-Install SGLang: See [https://sgl-project.github.io/start/install.html](https://sgl-project.github.io/start/install.html)
-
-Send requests: See [https://sgl-project.github.io/start/send_request.html](https://sgl-project.github.io/start/send_request.html)
-
-## Backend: SGLang Runtime (SRT)
-See [https://sgl-project.github.io/backend/backend.html](https://sgl-project.github.io/backend/backend.html)
-
-## Frontend: Structured Generation Language (SGLang)
-See [https://sgl-project.github.io/frontend/frontend.html](https://sgl-project.github.io/frontend/frontend.html)
+- [Install SGLang](https://sgl-project.github.io/start/install.html)
+- [Send requests](https://sgl-project.github.io/start/send_request.html)
+- [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
 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/)
@@ -343,6 +349,9 @@ Learn more in our release blogs: [v0.2 blog](https://lmsys.org/blog/2024-07-25-s
 ## Roadmap
 [Development Roadmap (2024 Q4)](https://github.com/sgl-project/sglang/issues/1487)
 
-## Citation And Acknowledgment
+## Adoption and Sponsorship
+The project is supported by (alphabetically): AMD, Baseten, Etched, Hyperbolic, Jam & Tea Studios, LinkedIn, NVIDIA, RunPod, Stanford, UC Berkeley, and xAI.
+
+## 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.
-We also 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-0.3.6.post1.dist-info/RECORD

@@ -0,0 +1,164 @@
+sglang/__init__.py,sha256=3M0oz0ZA8fULhV5LwQ4hxh-MRdHsOJRD1D63C60pdG4,1616
+sglang/api.py,sha256=NdO6cYnklnEBQBKqQjlqI8-P1EownKQ71t5ibCGhEVo,6953
+sglang/bench_latency.py,sha256=oZjSAzX7dUiSu-zdz0dkyUPo-qAX_lsXFH1gf03akgI,76
+sglang/bench_offline_throughput.py,sha256=z6uA6Gxa_nFZa0cOXi7MJDuX82xcqk5WfqBMavd8a-s,10929
+sglang/bench_one_batch.py,sha256=WxrQUkMcxz5GV8OEHj0ckHgpC76HgO6YxmDvJFRDeyU,15670
+sglang/bench_one_batch_server.py,sha256=nzeF_bcaXanQuYLBxAvd3OO4fwbKproMcahXdHIVR6w,5920
+sglang/bench_serving.py,sha256=hI7FjaERyqKBrYtKewDU6E4rSufKxqsUPyUgtWtTKSI,52545
+sglang/check_env.py,sha256=nR2m0a9WbQmkimJihUx-Lqi7XjN0jyWTCO2vYyA7R2M,5356
+sglang/global_config.py,sha256=fnT0U9vlHdGaQFKN9tYTnUF4-eVW4HYQURd5zvPtrg0,1286
+sglang/launch_server.py,sha256=_XIqBcXArYtHTqilOFkYWKZBYXGCMHAxbYOST08LGj0,415
+sglang/launch_server_llavavid.py,sha256=tGc17S1vUfLwbi1GB26oOdXxTWr7gjlqpTrPnrMRNO8,1007
+sglang/utils.py,sha256=eCvD3fZCALr-MuyZxJL7HAeeqqpxAxf4LJrf7OiCbco,11547
+sglang/version.py,sha256=YrfhKDmn6rTAj_qREKEXk2FahHCqSbHd4BNoD7wlIi0,28
+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
+sglang/lang/compiler.py,sha256=o1C6G3TzhjSlsH-doTPy5oiVehr57dxNTa5oZw5TTAI,7639
+sglang/lang/interpreter.py,sha256=SBjejhLhTKzNM0HbjtTg5r17WPJ64WFSk6lcM_SCWKs,30717
+sglang/lang/ir.py,sha256=zpzzAO1YVldhE95Vwz5hU_TQltu-xt8A6rfFr0PuIDA,18410
+sglang/lang/tracer.py,sha256=borJmlSJOhg1RUndGRnilnR60eEZz2Y9aU7BpftsOxU,8287
+sglang/lang/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+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/runtime_endpoint.py,sha256=IWbrAKrUkzNOvwV6V9_y6pkTr2SUYEkKBT-3kirgad0,10514
+sglang/lang/backend/vertexai.py,sha256=O-iBLD-y3vq80UxnrAoJri7bxpgd-_eakZ88Cf8bEGA,4855
+sglang/srt/conversation.py,sha256=u9zFU8aMYzwHUbQRKU76B_T-jfLlPoxUcWG_nRbDM2I,21201
+sglang/srt/hf_transformers_utils.py,sha256=sUUCpjbTHuYDMuwOaz00nH5fataXKjliD8gCxXU64sw,6712
+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=7PSxAUhiS796yQFeiQxiilRhLQ3FpV0wL53CfDgkCIk,30851
+sglang/srt/server_args.py,sha256=CfmpU6_EDnxJzpJiRx2n6AhOPCtrHPOf-7wEtTF__L0,30834
+sglang/srt/utils.py,sha256=APZEUancLC0jRI1JMbv7e5bIZy3OEySGyZspxGA60yQ,33509
+sglang/srt/configs/__init__.py,sha256=_usVIXHQjft4PAJ1Y-yGQOn2QNOv501GYMlQwpGXbns,208
+sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
+sglang/srt/configs/model_config.py,sha256=dQ58mYKN3M5IwldFZkwIb4CCBa6dREb5Om4Kg2kffOE,9565
+sglang/srt/configs/qwen2vl.py,sha256=AYHuFgJ0bwhWYkD7S6fvP7yJejJnuhy4xp5Q2W-O6ps,4424
+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=IDpyzXJS-ydRXYOHHzx1bO9VjiMRF8E5knn4CLFwPU8,6447
+sglang/srt/constrained/outlines_jump_forward.py,sha256=IGg6mThDepugfez0jnQ6HfLSHtiUl_Mq7bsPFppb3DA,6196
+sglang/srt/constrained/xgrammar_backend.py,sha256=4ZCQgcjWEY2Lg4r2V9sAiYJJblkQ_uVbEnvsjqhR1Pc,4548
+sglang/srt/layers/activation.py,sha256=EboMjT9HV2tNHQ6rzpojtlkzev1lAFbhQlxMg9hwxBQ,5471
+sglang/srt/layers/custom_op_util.py,sha256=0vu-yX2wwonmO1L_o5G7SA6C-8XuhDIh9rPDvNeLhoc,922
+sglang/srt/layers/fused_moe_patch.py,sha256=dxjcBMY_zAqA0pnmy5KDUZZJSd5Q64Xlxhxyb33cdMk,4240
+sglang/srt/layers/layernorm.py,sha256=nRQ1w1xSUcU-zlqVC61BnGG6otS5W1w9VaSzeXizrx4,4037
+sglang/srt/layers/linear.py,sha256=EOdlpAf6srqxzvPpxcv10KFJKedNc22CGP1qEvpRbDg,46131
+sglang/srt/layers/logits_processor.py,sha256=V8fHxeQK8lzUhGD2Xc7MY1Y9qBhzFyh6hqp31RJVefg,12669
+sglang/srt/layers/pooler.py,sha256=rj2lygvleBnyLCBZ8I11HGMgpfIDsT0l3PIkshJwdu4,1606
+sglang/srt/layers/radix_attention.py,sha256=C_mK4mfmKlxMRNeKYP9E5R3PRd3eT-OcE_g3mo36dJM,2058
+sglang/srt/layers/rotary_embedding.py,sha256=29tx3JNR40AoXqBa2cFGBjva9vU2xgFipETlpMaaZas,3985
+sglang/srt/layers/sampler.py,sha256=zgNwgUx7fozkWsEJFRKDV9SipHBijfpU9pTroNst6Ho,4552
+sglang/srt/layers/torchao_utils.py,sha256=v0hyr4hLsM42QwOPCdKb-ftRTjVokBZbqvRj4O4C-Nw,3415
+sglang/srt/layers/vocab_parallel_embedding.py,sha256=RmaZbgXbFnGKX1eGYxlmiko-6JwaJX6seHupUSCtAm8,21583
+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=oblYMbmYzK94H3EA9lMhKWaKdi8HLH5NqAiZmjzj4Es,24875
+sglang/srt/layers/attention/triton_backend.py,sha256=gjxed2cvc2-8QEHkzyTVv6ui7oYOp2b_vgIUQVD1XuM,6538
+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/prefill_attention.py,sha256=lojFXRZMLWkzS2Y8uxaolnQhXaWKG19mCAWaF5KQeiI,6087
+sglang/srt/layers/fused_moe_grok/__init__.py,sha256=rj_JBzcP--eaaM6LGQ-u580uQvqLisp5JtGBAs1fVYc,80
+sglang/srt/layers/fused_moe_grok/fused_moe.py,sha256=bxRcjdALxeY3FDnKivGOoNr6Er1kh6CCPtlAp7pjz50,23844
+sglang/srt/layers/fused_moe_grok/layer.py,sha256=v-o5YHYEU2HIEZwouyuc3UyfNj7YQrEYOO_BXKELU7Y,23453
+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=f9tCC_9sHjp7JCPvyZIvuoTB4KooIucGA9S2w7ADevw,4849
+sglang/srt/layers/quantization/base_config.py,sha256=daK9p0aijMszLUm1W4Pc33FK87MdqYK1NoWFKif-j80,4599
+sglang/srt/lora/lora.py,sha256=KhhO9aKCyFWvJnhI07lZKANIvNjtt882HrTYFNBZMv0,15065
+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=JxRtJJTVn1FU2iD292rLZPftAsR4_8j4d3yF8j0dvBc,8327
+sglang/srt/managers/detokenizer_manager.py,sha256=nWBn54pz3aQ8tzVvViwwL2k0V4WATi0qw11H0Bzua-Q,7389
+sglang/srt/managers/image_processor.py,sha256=Pk_dtXzljTkFt7Acsv1RyDzEqvCvjc7BMngxGhtkpDU,13817
+sglang/srt/managers/io_struct.py,sha256=WLXz-tyn0jR7zNO9feRBXgyjphVa8qR55OoEOUdzoVI,13751
+sglang/srt/managers/schedule_batch.py,sha256=-5oYdkStPiYjPWl0tCkUVRjTGB7fjA0wIngK-09da7w,43111
+sglang/srt/managers/schedule_policy.py,sha256=ayFz4iPLIlG8mx5i1glTCAMHJPGpFedMP9UgRtqkNhA,12526
+sglang/srt/managers/scheduler.py,sha256=8owHPXG6fxZtsCWSJ6K7EOlFDcPxYinZC1DwKMJcEVM,55930
+sglang/srt/managers/session_controller.py,sha256=jXoPHxMGh8T1iYWIEjSXoPVwaL6NEjv3QtqlsrvPE1c,2355
+sglang/srt/managers/tokenizer_manager.py,sha256=zYbKEKNuM1B3PXzA7jnDpxew-0rZXSX-7dHmVLWG3e4,26477
+sglang/srt/managers/tp_worker.py,sha256=1SQJ60iKS9e5vGY555fT1iZ4OtLumXzeWfB08fSWKbk,6176
+sglang/srt/managers/tp_worker_overlap_thread.py,sha256=7vhPebaOS4JamaS08CGf_hwxnUO7Gy_SXZXEPwNHKoY,7621
+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/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=4hbCtE3gt5kvMNHrnxkE8YPRFcgmVo0Bwz3lgbYZw_E,14805
+sglang/srt/model_executor/forward_batch_info.py,sha256=n5yk927COTU0klDAkQuwrFzamMygfkHxmDp1I6bJYD8,12612
+sglang/srt/model_executor/model_runner.py,sha256=AafFWd_EDWbOe0o5etAyutGum5O8_9tO55KRcaAWDW4,29680
+sglang/srt/models/baichuan.py,sha256=RyvPQvi7wy9VUGvLwG17XttcTp43yRj6c3zNRImBToA,15005
+sglang/srt/models/chatglm.py,sha256=OikygdK8Mi6F2QPPhAr2E_P4l2V0yWQjDJOdnBAApPE,13216
+sglang/srt/models/commandr.py,sha256=XkzpfsdDPDx-W5oOac8nFIe39JJZvmv65K5GIpgJTz0,14212
+sglang/srt/models/dbrx.py,sha256=ucn3UJ1s4nx2qa5hUb8VhJmfVrDZ59e9oNetMU5EWq8,14624
+sglang/srt/models/deepseek.py,sha256=B5OuW--kDIPfZesOhvGGUhHQNWh0pMPNCYmdsv9lv5U,15922
+sglang/srt/models/deepseek_v2.py,sha256=shdHVtZGmLEZMZwGlIPz8NPoSb1c_n6hQxWKG45WahE,32265
+sglang/srt/models/exaone.py,sha256=6LJ1Mr9MbHOXdH_nK9Dba3SR28LMCJvdH1k53w9M9Vg,13081
+sglang/srt/models/gemma.py,sha256=079CfoQqBnrLIbW0LWcLp-nmb1aPVN1Tw6PxMQQ3Lsk,12289
+sglang/srt/models/gemma2.py,sha256=lbfQhQpUhf1MAEB_00Uo6rp20k4Hr353UbPKKuMsxec,15020
+sglang/srt/models/gemma2_reward.py,sha256=cQawatbsfBuWQTueivYHl_17ZoQUHEelI1sr1y5pvfY,2556
+sglang/srt/models/gpt2.py,sha256=Th7_Dnkw82GFBOuMOTrHtA44JBPHRUtY3Qd73rQwzMc,9741
+sglang/srt/models/gpt_bigcode.py,sha256=lYo4ajy49VvvPkaduaFtOaCRT_ItqyNUE158S-BI5QA,10136
+sglang/srt/models/grok.py,sha256=rDIH_SFzauuEHcL_vCOSrYLjdBC3i3o_AcceL3amsJw,14927
+sglang/srt/models/internlm2.py,sha256=DxbA15d9QR0tLOczpC6DkB8QyNHXJRdZatY6Nskwv1k,12170
+sglang/srt/models/internlm2_reward.py,sha256=Lr-JA0vfTQJt9q5oDMiopGuoXAevyEv5PAoDe2rsTJk,2425
+sglang/srt/models/llama.py,sha256=FSGuM3BamhuT5h2jedh5cSFwFYduOJwkAZJJ672awRw,16423
+sglang/srt/models/llama_classification.py,sha256=c8WZ1ADa3f6s2IJVoP10ouVgeCwv_ndns_qMgLrC6QI,3413
+sglang/srt/models/llama_embedding.py,sha256=2ex2jrz31osaAd9V8sJeN0qyxmk-L5NgOBkXL1puGhI,3166
+sglang/srt/models/llama_reward.py,sha256=prhHDPpf1k6tlQtGE6zq5gx0uSZAD3W5v7W28bdgy4U,4619
+sglang/srt/models/llava.py,sha256=72DnZXIwu78zYqU8YIElq_AaSIFO_icYOPTHXE0_-YQ,24941
+sglang/srt/models/llavavid.py,sha256=DeWqGSmXgIYGuLyy2ZrxjM9WqbRjueP4chNmXt7Bnus,12221
+sglang/srt/models/minicpm.py,sha256=KbiTf-kaDAJxSo9Z4IGMTrs9WrYYji1KXO1kA2iy-as,13816
+sglang/srt/models/minicpm3.py,sha256=C43mTr2Qjccj4sXuTDgzbfZhvCNbsEHNggMRXQ7SrWs,25108
+sglang/srt/models/mistral.py,sha256=EYifJUUzN2Z2-iL37eJiNZF_DB0H4pa0mKlgYRIxM70,838
+sglang/srt/models/mixtral.py,sha256=E3d8I7V3Dp1nCEHRbhh-PKBG8UaVK5XOHwl9QyIjcX0,14043
+sglang/srt/models/mixtral_quant.py,sha256=o-oTG8BGtWuNu-o6muHSarMNBQwrjQowyBFOQhuclZ8,14065
+sglang/srt/models/mllama.py,sha256=pET1x8wY04yoS8HMCncKx0tFPqGp78K8rlA7Eq7XioE,37889
+sglang/srt/models/olmo.py,sha256=DEUPNDM0z83N-Qdhkj2WJMtbiz5JNbSBMIjUaYZN9RM,12068
+sglang/srt/models/olmoe.py,sha256=jVKrjqQQrWLdlkGSGUaMPdT9PHzNH4X-RVwON29eaGw,15412
+sglang/srt/models/phi3_small.py,sha256=fxqGU0xphJzTeuBW38SRRYpRb2rcsg53JxuObK0pZig,15141
+sglang/srt/models/qwen.py,sha256=P9zcFnz_Tsz73tVtLRwZ8uWzCtMxWOrzlv2o9Ys_Gck,9947
+sglang/srt/models/qwen2.py,sha256=ApFFASNwvrkDXi-KkCNA7fTk4uLMuJWoMg15zCaAKdA,12514
+sglang/srt/models/qwen2_moe.py,sha256=1oxDsKDq3jlHKx9jMi1SfHOqCRVyN5n76uw3M-CUODE,17048
+sglang/srt/models/qwen2_vl.py,sha256=G3FNa_N2-CzB56LVrukwBtJazxMrDC_GPNjK6Wqxc4s,26415
+sglang/srt/models/stablelm.py,sha256=jpmsyWMJo_9JapOESnuV7ObNCh78BRznXY0iFvvIbZE,11354
+sglang/srt/models/torch_native_llama.py,sha256=vNQxsnbVAY1bdyMCCWDZAtWdbaFIiJXhmVxHjk5BB9Y,19400
+sglang/srt/models/xverse.py,sha256=LGe0ma0wOir3x-OLBT_cRocw8JEo9d3AYNxgA2OcLrk,13659
+sglang/srt/models/xverse_moe.py,sha256=YqbzkSsnTFt-8-aI8YobF9qJA70qrBjbS1Kjn1KNqVY,15766
+sglang/srt/models/yivl.py,sha256=yj4aWsOBVGQBLurSrLmYXVC7zGIPH7EYHHtAaAZ7Liw,4859
+sglang/srt/openai_api/adapter.py,sha256=MhOcWZjcLv4_OuvLvDMcAu6K_u2joJvhaZxaKm0hi3M,53634
+sglang/srt/openai_api/protocol.py,sha256=vBgrbTqtECsZ5dG0rgP1FHsTBt4eR9zbDX3FBIN-rz4,10172
+sglang/srt/sampling/sampling_batch_info.py,sha256=YC-KPyDWyLGNPL4YVcst4xwP8Wlz2zcCNJHB_5zljXQ,8470
+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
+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/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
+sglang/test/runners.py,sha256=ANzjrHkT_1E0G3UcD47O8XEKst3Si4AOfx-uErbFS7o,15129
+sglang/test/simple_eval_common.py,sha256=joqrGysuLnJFtzDRIgFkMsRyKUSyjVPFWp0_PHAL3Ik,12378
+sglang/test/simple_eval_gpqa.py,sha256=8Xt9Bw05c7SZTYrCZgB68OZUqUbLo69ywiyx0bTvSUk,3220
+sglang/test/simple_eval_humaneval.py,sha256=zmV3xWYc2OrpiT9Dy55RTKZL5DEROD1cJ0NA_-cU5zI,5685
+sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWUpk,2550
+sglang/test/simple_eval_mgsm.py,sha256=rd7TSUyxdKbrXaVoewo24V8lCo_6kO8zxPhhmvylpw8,10259
+sglang/test/simple_eval_mmlu.py,sha256=FkwamjGMjueTixymkedF-YiPloSLiy4ftILFUrKZ9XI,4357
+sglang/test/test_activation.py,sha256=jkdNRzJnbd5OgZliQaIXpxovlcky17UrweomcOcMxoE,1442
+sglang/test/test_layernorm.py,sha256=IacByD5d-stXjzBz8Ypamc7povlcedpKPbb_4JLgo3c,3720
+sglang/test/test_programs.py,sha256=1Z0umrsUu9pagzyGH5SrXl_qhKSyTfUv_kWC2mcn0qo,18208
+sglang/test/test_utils.py,sha256=ULF7C3pLXkMevXgE_Dodt29OBfvvXKUnRvwKhaBg1ys,23470
+sglang/test/srt/sampling/penaltylib/utils.py,sha256=CjxHgywh0hx_87iynzQt_ztHu6zBVuE-YrZ-XPmW6U4,12906
+sglang-0.3.6.post1.dist-info/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
+sglang-0.3.6.post1.dist-info/METADATA,sha256=XwhCEL8SbEVcT7LQLk26g6tzduS6mByBE7dDqZYpQxo,22073
+sglang-0.3.6.post1.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+sglang-0.3.6.post1.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
+sglang-0.3.6.post1.dist-info/RECORD,,

{sglang-0.3.5.post2.dist-info → sglang-0.3.6.post1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.5.0)
+Generator: setuptools (75.6.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

sglang/srt/layers/fused_moe/__init__.py

@@ -1 +0,0 @@
-from sglang.srt.layers.fused_moe.layer import FusedMoE, FusedMoEMethodBase