sglang 0.3.0__py3-none-any.whl → 0.3.1__py3-none-any.whl

{sglang-0.3.0.dist-info → sglang-0.3.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sglang
-Version: 0.3.0
+Version: 0.3.1
 Summary: SGLang is yet another fast serving framework for large language models and vision language models.
 License: Apache License
                                    Version 2.0, January 2004
@@ -242,6 +242,7 @@ Requires-Dist: psutil; extra == "srt"
 Requires-Dist: pydantic; extra == "srt"
 Requires-Dist: python-multipart; extra == "srt"
 Requires-Dist: torch; extra == "srt"
+Requires-Dist: torchao; extra == "srt"
 Requires-Dist: uvicorn; extra == "srt"
 Requires-Dist: uvloop; extra == "srt"
 Requires-Dist: zmq; extra == "srt"
@@ -253,6 +254,7 @@ Requires-Dist: matplotlib; extra == "test"
 Requires-Dist: pandas; extra == "test"
 Requires-Dist: sentence-transformers; extra == "test"
 Requires-Dist: accelerate; extra == "test"
+Requires-Dist: peft; extra == "test"
 
 <div align="center">
 <img src="https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png" alt="logo" width="400"></img>
@@ -271,14 +273,16 @@ Requires-Dist: accelerate; extra == "test"
 
 SGLang is a fast serving framework for large language models and vision language models.
 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**: Efficient serving with RadixAttention for prefix caching, jump-forward constrained decoding, continuous batching, token attention (paged attention), tensor parallelism, FlashInfer kernels, and quantization (AWQ/FP8/GPTQ/Marlin).
-- **Flexible Frontend Language**: Enables easy programming of LLM applications with chained generation calls, advanced prompting, control flow, multiple modalities, parallelism, and external interactions.
+
+- **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).
+- **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 3, Gemma 2, Mistral, QWen, DeepSeek, LLaVA, etc.) and embedding models (e5-mistral), with easy extensibility for integrating new models.
+- **Active Community**: SGLang is open-source and backed by an active community with industry adoption, welcoming contributions to improve LLM and VLM serving.
 
 ## News
+- [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/)).
-- [2024/08] 🔥 LLaVA-OneVision with single-image, multi-image and video are supported ([blog](https://llava-vl.github.io/blog/2024-08-05-llava-onevision/)).
 - [2024/02] SGLang enables **3x faster JSON decoding** with compressed finite state machine ([blog](https://lmsys.org/blog/2024-02-05-compressed-fsm/)).
 
 <details>
@@ -300,6 +304,8 @@ The core features include:
 
 ## Install
 
+You can install SGLang using any of the methods below.
+
 ### Method 1: With pip
 ```
 pip install --upgrade pip
@@ -312,7 +318,7 @@ pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/
 ### Method 2: From source
 ```
 # Use the last release branch
-git clone -b v0.3.0 https://github.com/sgl-project/sglang.git
+git clone -b v0.3.1 https://github.com/sgl-project/sglang.git
 cd sglang
 
 pip install --upgrade pip
@@ -323,7 +329,7 @@ pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/
 ```
 
 ### Method 3: Using docker
-The docker images are available on Docker Hub as [lmsysorg/sglang](https://hub.docker.com/r/lmsysorg/sglang/tags), built from [Dockerfile](docker).
+The docker images are available on Docker Hub as [lmsysorg/sglang](https://hub.docker.com/r/lmsysorg/sglang/tags), built from [Dockerfile](https://github.com/sgl-project/sglang/tree/main/docker).
 Replace `<secret>` below with your huggingface hub [token](https://huggingface.co/docs/hub/en/security-tokens).
 
 ```bash
@@ -391,7 +397,7 @@ sky status --endpoint 30000 sglang
 
 
 ### Common Notes
-- [FlashInfer](https://github.com/flashinfer-ai/flashinfer) is currently one of the dependencies that must be installed for SGLang. It only supports sm75 and above. If you encounter any FlashInfer-related issues on sm75+ devices (e.g., T4, A10, A100, L4, L40S, H100), consider using Triton's kernel by `--disable-flashinfer --disable-flashinfer-sampling` and raise an issue.
+- [FlashInfer](https://github.com/flashinfer-ai/flashinfer) is the default attention kernel backend. It only supports sm75 and above. If you encounter any FlashInfer-related issues on sm75+ devices (e.g., T4, A10, A100, L4, L40S, H100), please switch to other kernels by adding `--attention-backend triton --sampling-backend pytorch` and open an issue on GitHub.
 - If you only need to use the OpenAI backend, you can avoid installing other dependencies by using `pip install "sglang[openai]"`.
 
 ## Backend: SGLang Runtime (SRT)
@@ -457,24 +463,29 @@ print(response)
 It supports streaming, vision, and most features of the Chat/Completions/Models/Batch endpoints specified by the [OpenAI API Reference](https://platform.openai.com/docs/api-reference/).
 
 ### Additional Server Arguments
-- Add `--tp 2` to enable multi-GPU tensor parallelism. If it reports the error "peer access is not supported between these two devices", add `--enable-p2p-check` to the server launch command.
+- To enable multi-GPU tensor parallelism, add `--tp 2`. If it reports the error "peer access is not supported between these two devices", add `--enable-p2p-check` to the server launch command.
 ```
-python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000 --tp 2
+python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --tp 2
 ```
-- Add `--dp 2` to enable multi-GPU data parallelism. Data parallelism is better for throughput if there is enough memory. It can also be used together with tensor parallelism. The following command uses 4 GPUs in total.
+- To enable multi-GPU data parallelism, add `--dp 2`. Data parallelism is better for throughput if there is enough memory. It can also be used together with tensor parallelism. The following command uses 4 GPUs in total.
 ```
-python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000 --dp 2 --tp 2
+python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --dp 2 --tp 2
 ```
 - If you see out-of-memory errors during serving, try to reduce the memory usage of the KV cache pool by setting a smaller value of `--mem-fraction-static`. The default value is `0.9`.
 ```
-python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000 --mem-fraction-static 0.7
+python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --mem-fraction-static 0.7
 ```
 - See [hyperparameter_tuning.md](docs/en/hyperparameter_tuning.md) on tuning hyperparameters for better performance.
 - If you see out-of-memory errors during prefill for long prompts, try to set a smaller chunked prefill size.
 ```
-python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --port 30000 --chunked-prefill-size 4096
+python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --chunked-prefill-size 4096
 ```
-- Add `--nnodes 2` to run tensor parallelism on multiple nodes. If you have two nodes with two GPUs on each node and want to run TP=4, let `sgl-dev-0` be the hostname of the first node and `50000` be an available port.
+- To enable torch.compile acceleration, add `--enable-torch-compile`. It accelerates small models on small batch sizes.
+- To enable fp8 weight quantization, add `--quantization fp8` on a fp16 checkpoint or directly load a fp8 checkpoint without specifying any arguments.
+- To enable fp8 kv cache quantization, add `--kv-cache-dtype fp8_e5m2`.
+- To enable DeepSeek MLA acceleration, add `--enable-mla`.
+- If the model does not have a chat template in the Hugging Face tokenizer, you can specify a [custom chat template](docs/en/custom_chat_template.md).
+- To run tensor parallelism on multiple nodes, add `--nnodes 2`. If you have two nodes with two GPUs on each node and want to run TP=4, let `sgl-dev-0` be the hostname of the first node and `50000` be an available port.
 ```
 # Node 0
 python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --tp 4 --nccl-init sgl-dev-0:50000 --nnodes 2 --node-rank 0
@@ -482,9 +493,6 @@ python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct
 # Node 1
 python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --tp 4 --nccl-init sgl-dev-0:50000 --nnodes 2 --node-rank 1
 ```
-- If the model does not have a template in the Hugging Face tokenizer, you can specify a [custom chat template](docs/en/custom_chat_template.md).
-- To enable experimental torch.compile support, you can add `--enable-torch-compile`. It accelerates small models on small batch sizes.
-- To enable fp8 quantization, you can add `--quantization fp8` on a fp16 checkpoint or directly load a fp8 checkpoint without specifying any arguments.
  
 ### Supported Models
 
@@ -510,6 +518,10 @@ python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct
 - ChatGLM
 - InternLM 2
 - Exaone 3
+- BaiChuan2
+- MiniCPM / MiniCPM 3
+- XVERSE / XVERSE MoE
+
 
 **Embedding Models**
 

sglang-0.3.1.dist-info/RECORD

@@ -0,0 +1,129 @@
+sglang/__init__.py,sha256=T8MYdFfKFPZcgFKHMBpOCIlFbhjwmr77Nqm6mdE6bCY,1590
+sglang/api.py,sha256=pH4CjwOXUweL5MF1sIkFMddDxfnF7PyUxEHC5kvNVbI,6468
+sglang/bench_latency.py,sha256=EvmXpaREU-g25OTcOUTgAUPmA-txfnyjaqY-4hlq97w,16925
+sglang/bench_serving.py,sha256=6OM5JIDuoxJDg-VLE4ijGGcS8-6ViaidV05lIrZmSzo,36239
+sglang/check_env.py,sha256=rGRABCgt-0SfUrow4px28b2P59aMn8eVTnN5eZc_a8s,5397
+sglang/global_config.py,sha256=KWpXd4OCCWW2TRQo-dShvLs4jb15ej9Ejhxr_wggzBg,1535
+sglang/launch_server.py,sha256=UnjNjYuZ8TtvmRtgYEsFImkbvCwvn_tQjk0V7cHy67E,450
+sglang/launch_server_llavavid.py,sha256=olPKyhozi1coCwoRMwBRYWsTFByrgus9CwPSeNmskgc,1002
+sglang/utils.py,sha256=NA_4xUrTI7KICQ3PEACfNWKE3nxSA5QvQZJNd4TQrDc,9395
+sglang/version.py,sha256=r4xAFihOf72W9TD-lpMi6ntWSTKTP2SlzKP1ytkjRbI,22
+sglang/lang/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+sglang/lang/chat_template.py,sha256=uqI_I9zIKXGXg7-W-yjqvx1ZeS_TuwFCms6wkmC2QmY,13411
+sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
+sglang/lang/compiler.py,sha256=o1C6G3TzhjSlsH-doTPy5oiVehr57dxNTa5oZw5TTAI,7639
+sglang/lang/interpreter.py,sha256=M42SuOnijFaHWOe3Qyi-bNanRt-mYhSDa1wWn1J42Hw,30324
+sglang/lang/ir.py,sha256=W3UfZikcGeT86PDDjDjw-yNzrKY2e2UYO4DTatMCfm0,17704
+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=Q5HdiDtyBewQeoYH0kDtBRVL8KFiEPNq9dw7XmauHQ8,1985
+sglang/lang/backend/litellm.py,sha256=ugmL7sfUxkUHVbHtwNzHgdQAEd4UCjNQboFuE3KThcY,2450
+sglang/lang/backend/openai.py,sha256=qM7eVH_kMxnDd2rpxOH0v76KxtOJFlAwgLgWIKvFGCI,15060
+sglang/lang/backend/runtime_endpoint.py,sha256=MEyMl5cIAMwaWmp4j0HtuCOQ_XdJoyywztvAOGsicao,9832
+sglang/lang/backend/vertexai.py,sha256=O-iBLD-y3vq80UxnrAoJri7bxpgd-_eakZ88Cf8bEGA,4855
+sglang/srt/conversation.py,sha256=S5w5V6G1xigNxa3UQoSxRcMpQLWWDT9EPBoHBvHkSAk,19663
+sglang/srt/hf_transformers_utils.py,sha256=6HlqcmGPIvnSGaEEICeuzwag1QylSoSGbXRVvUdIMDo,6016
+sglang/srt/mm_utils.py,sha256=zox644S3IHUWmADdK4MnIbdTS2DWHOy0_Dq0gCU38QQ,12273
+sglang/srt/server.py,sha256=FNmTpX7E9fVWj_NFzp4AtE5ODaA_rg5Xm8uZ0FB0X4o,20041
+sglang/srt/server_args.py,sha256=5OHH3gaO1s5Y2UQw2_FnFxwxrsqnUQ_WNqP1R1IWUAA,21877
+sglang/srt/utils.py,sha256=pckOt7gyQfJaV3-h8FPurWyrPij5_EBUX_Xp7x6y6YM,24229
+sglang/srt/configs/__init__.py,sha256=292SuEorST-lAq2Uvsv2M7yC28uYZlssVvRDsF-bZCQ,86
+sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
+sglang/srt/configs/model_config.py,sha256=OqHrucJQHbH-wxgkGj-Dcx_B888uUGASpLRjz40HaLY,6651
+sglang/srt/constrained/__init__.py,sha256=ze8awDPvwAzdeMwzJ-25kXOQ4nVWoaP55jBDt5UOS_4,2070
+sglang/srt/constrained/base_tool_cache.py,sha256=5sazBMHHDpHMoqOjuY6itCxwTmIFCflIWEDXMtmrPVs,2006
+sglang/srt/constrained/fsm_cache.py,sha256=jItSvCu_XrAgltfejwgvdltaiT98-8lJGBe_84cSnTk,2786
+sglang/srt/constrained/jump_forward.py,sha256=9_HxmXtWjr5S6a5e0cBimbY3ZhiLiJC74V6jIqDXfuo,6575
+sglang/srt/layers/activation.py,sha256=JEXNTgqxoiU4N-gVm4XMjobhft4JKDcMrgTkfpsRUzM,4856
+sglang/srt/layers/attention_backend.py,sha256=39P3iMs7B1iEzCA3EHdqUp3BLafeIVFnFWGzpEhlTRk,18182
+sglang/srt/layers/flashinfer_utils.py,sha256=jyaO7XiEisFZg_dfaCbfRCHSHSKYoM1wOzfHa0h1q14,7413
+sglang/srt/layers/layernorm.py,sha256=RXuS4UyksatqTF6lSK7VYyEiUEnBiNIBlEn8q4w84UA,3404
+sglang/srt/layers/logits_processor.py,sha256=Js2qSk1Z3uPL2cYO1ARai51f2i8OedV3qdwByQVSJtI,12439
+sglang/srt/layers/pooler.py,sha256=qNMG3Ycvt2yf9mk1Lcs-2K7oPeCuVeDYoHAxkMu9b_Q,1610
+sglang/srt/layers/radix_attention.py,sha256=EcVO0fUSmgvE_9R-MlpgJq0O_uT8ACuHzbMi19bANYc,1874
+sglang/srt/layers/sampler.py,sha256=1BKsZbSLBGFVtTJo1LsThuoRjOSOnsL1AiwFxJNIXRs,5800
+sglang/srt/layers/torchao_utils.py,sha256=rTECwKSXhj_ylh_iSzfbopz9_lZOFHatquQrNJNLZlE,2703
+sglang/srt/layers/fused_moe/__init__.py,sha256=bWCrDdOy2ANEXTb8CHYO63O3Iu3eZnn0PJbgl0z5vvE,75
+sglang/srt/layers/fused_moe/fused_moe.py,sha256=1WM2cObWXcFWtqh_utGJFPnrT344rORwuQ9hJDaH2s0,23104
+sglang/srt/layers/fused_moe/layer.py,sha256=GT3r2UPx_PAufJd0SUMOXyh76ymAeYDubd0SM0H71bo,20977
+sglang/srt/layers/triton_attention/decode_attention.py,sha256=XCQTX0kUttT1AG5FRMgfQbiXgvoempYD0UR2r6D_vJg,16711
+sglang/srt/layers/triton_attention/extend_attention.py,sha256=XTUTMrE-5jfMEufQUifZ-8NJQABSPcF47qhnNT5Z1iI,11050
+sglang/srt/layers/triton_attention/prefill_attention.py,sha256=QkXPcT02c13zha2M4mBm2S5dh_sS-Gc4FkkrcywRqvc,5377
+sglang/srt/lora/lora.py,sha256=ksj866lgDul6zxO30Jm7Nrjv-mFAMrzdvP8sez3Pl6U,14938
+sglang/srt/lora/lora_config.py,sha256=paVB7F7SIuxr_vodvKf8zzAlH2fdVYHhXxcXV62D0Vo,1411
+sglang/srt/lora/lora_manager.py,sha256=Q7rk1SMEZ75wda68rAZDGVyX_o8ZdIW2I5Fo_llaqHs,9475
+sglang/srt/managers/controller_multi.py,sha256=KolZDso2WqH1ZhQw9p1eTmlFRgo4bcvzBxE44_sNE_o,6300
+sglang/srt/managers/controller_single.py,sha256=DiZALP_iIPZQMRx09a-LwT5_Dg7p-WU8HXyMoxJ9sRA,4955
+sglang/srt/managers/detokenizer_manager.py,sha256=yQkL5gLomLiy1qc6e9HNz8hcj7JQFHm1AfIrzpXaWJE,6852
+sglang/srt/managers/io_struct.py,sha256=bqmL3NDPLqOn6Au3WLF0NOe8Dh7ECMN7BTHCkEZ_Edk,11247
+sglang/srt/managers/policy_scheduler.py,sha256=tiBUi2GJU5eQEBK6HfsO1_YjWtFkougo40954DIp4dM,13026
+sglang/srt/managers/schedule_batch.py,sha256=QfixWzh7ks60eYE52mZHfUseXqcb89h4ZO1Aur3weLU,27340
+sglang/srt/managers/tokenizer_manager.py,sha256=ql-sObjl1oRigJwnLtqqTaaw-i7gPTDMoNXDEMftr40,29643
+sglang/srt/managers/tp_worker.py,sha256=Zbl_tFUAsD6Qv1fUEJCn_jyUc3JjDm33yI3Nmu1HY8w,39174
+sglang/srt/mem_cache/base_prefix_cache.py,sha256=qEQwEkG4E5rab2ZoTqcesf5pR_J4nV2jBxIHsBJHtIM,924
+sglang/srt/mem_cache/chunk_cache.py,sha256=CjZZYlqQzq7mYOiBMLWA5XNb6HIyh5lIMdY-K0OUZEc,2368
+sglang/srt/mem_cache/flush_cache.py,sha256=pTLKPRB17U6vl5RFJJvuJ4jCL2SyomgkUBNlkDpGRqo,978
+sglang/srt/mem_cache/memory_pool.py,sha256=4br3Ea2bfA-YsF_sPOVHlF2zQzYGd8fVaYTp197yZsE,7871
+sglang/srt/mem_cache/radix_cache.py,sha256=0AVr1BKKDOtTyybUkwxrz6PT8khDx-DpzgN5MgL27IE,10088
+sglang/srt/model_executor/cuda_graph_runner.py,sha256=LngmwtBcvobJ_9G8lD966SihjmMJlgMgHe_ZogK1kDg,10090
+sglang/srt/model_executor/forward_batch_info.py,sha256=yvkhayY9Zu6gysoojcGT73lADGOtfHKkFKWdJLRyACI,6141
+sglang/srt/model_executor/model_runner.py,sha256=7jBSCdZxyDLWMOdwv1vRa7Oue-xbp8lA6I11ZPKFdAc,23457
+sglang/srt/models/baichuan.py,sha256=NrG1rMJXhemkrUCEf8xKOSDQVsOD-nN8RQz6MWHOg84,15124
+sglang/srt/models/chatglm.py,sha256=KwxLHBEvK02McXDvBS0gnRxfIvOAu2QP7lgibrj9Nbc,13371
+sglang/srt/models/commandr.py,sha256=2rAXRZRb4PkJZ4NWEqP_rIgsjxbdZyHpuoMOarqTWzQ,14163
+sglang/srt/models/dbrx.py,sha256=N_0Ku_p1NCsc29NktUBNqPv7Z33XhYxOZK5xN7nzW4s,14661
+sglang/srt/models/deepseek.py,sha256=7UJgde1EV9ey6d-CKRcEyTKh1_WhZdatpZiltIuqpik,16006
+sglang/srt/models/deepseek_v2.py,sha256=3D9WtPvVOu8U40x_KOksnmWBLmLIcgtV958go8NSj5Q,28307
+sglang/srt/models/exaone.py,sha256=3I5ZoiLotf7U-8c9QJRubpgf6JDx9I_z-ViXQlCC-x8,13087
+sglang/srt/models/gemma.py,sha256=GkwgGFHgGlXgBZN7s7Wooz5tMyCp1YtgLahU2NOo66M,12273
+sglang/srt/models/gemma2.py,sha256=sFfCNEm0_OOWElRSTDuroRv8wNMX8v_81Uko9m546KA,14923
+sglang/srt/models/gpt_bigcode.py,sha256=kzHYogeGXZF4KHpkXA-RGqvs016mA-6klWxD2QJTi9E,10195
+sglang/srt/models/grok.py,sha256=6I4OwQwNyAbh5GF24_SRm12XYBvM9iGWB-T4TSTJ0wU,14929
+sglang/srt/models/internlm2.py,sha256=6j7JH0p3yib8GZDH8Cmrs-pgwfH3eOlAK6V3Cq64O7w,12202
+sglang/srt/models/llama.py,sha256=tjdjlIxJr31vgbzGBP_el9RgYxw1kzvmqnVinnTVVUw,15259
+sglang/srt/models/llama_classification.py,sha256=A2ABTUD5u4XoWv1dsIPU7wcCQP3jhbDJblMhLgaiFBA,3402
+sglang/srt/models/llama_embedding.py,sha256=RI2mpYheP5WwhuTINU-6IrU61usuMyCK9h2zDEyLW4g,3458
+sglang/srt/models/llava.py,sha256=O4XGdl70Hh4tM_OHapFGHbReC82mbe9xLw6GELKWKhU,24881
+sglang/srt/models/llavavid.py,sha256=ou5uIuskBoBo0lXvqFFfDLBYYVfehx27n-Lu8X9gpLs,11992
+sglang/srt/models/minicpm.py,sha256=ioqCsTCE_oF8xqGF5fm5cK9dclK5Y0EQ1UJfyteIDDo,13825
+sglang/srt/models/minicpm3.py,sha256=S7bNeCAsfvL44Vn350KLaqX674SCb4CpUuDnhjLjr3U,25113
+sglang/srt/models/mistral.py,sha256=tiYoKjyYVzlQl52QUZ33odD2yCxj9dxcqln474VuZOw,744
+sglang/srt/models/mixtral.py,sha256=oRC7mKBrPJhvzkWSabrbeQQQac-jtF4EV6H2Sgjc5JY,13897
+sglang/srt/models/mixtral_quant.py,sha256=wMACJq78OTWj7HlqPDRNEh8cjrVAjKqJEsOG3CO5xow,14072
+sglang/srt/models/qwen.py,sha256=nqSRzkiZzpRVG6WGQ1MBUclQnXyw8jlvoOq-euM8j5s,9954
+sglang/srt/models/qwen2.py,sha256=9_M-VkHN1_T1XN-gsl_L636QMQ9BLF2WqvTcx_1L6aw,12432
+sglang/srt/models/qwen2_moe.py,sha256=s7b5XnSvsBYtZZUkjPp442m59CqPJ3HxGUIwXBVWsXw,17153
+sglang/srt/models/stablelm.py,sha256=30ngpc0Xq3VxzXJlf6svP1oax8Q3krMJkxM8PVKtZWU,11359
+sglang/srt/models/xverse.py,sha256=luhp_90ZNkTpXHDCURO4MZBy1vbvHTVCwSe4PYYLWBs,13701
+sglang/srt/models/xverse_moe.py,sha256=YR--WZ33G7XEMsS7ZJl1cQ62Q8PDo9gWqpvJBY_cb-M,15886
+sglang/srt/models/yivl.py,sha256=B6MELthWIm5KdSzX3o2tbbpApY8XdjUdmcQSD4dQe_I,4835
+sglang/srt/openai_api/adapter.py,sha256=CJ47YftRHAip1FMcHIhtCorBtzlIkv7F0Wz_JUcI4T4,51032
+sglang/srt/openai_api/protocol.py,sha256=rdSwUAoO5-KLemJOE50xwSUagxY4T1QIiNyCYsTtCi0,9868
+sglang/srt/sampling/sampling_batch_info.py,sha256=vkwy59Jt51FESYukmwDKwPbCM45WMb16dx_408B3oqc,7900
+sglang/srt/sampling/sampling_params.py,sha256=ggOXxafqfCD-xrGYcM57byLZ79CIeBP4AD5F44L_CW0,5635
+sglang/srt/sampling/penaltylib/__init__.py,sha256=5vQw0Y5DSzmsoFg1IdMIKLwFVhYZ5ArADHVBYbSmOec,513
+sglang/srt/sampling/penaltylib/orchestrator.py,sha256=WkTNeDhj9H9rtp2ZZeX6MS2sdKSGlLboE6FcuKrwUo0,10815
+sglang/srt/sampling/penaltylib/penalizers/frequency_penalty.py,sha256=IvYioX53Vq_ji-0Zhcz_r5mUa3T3GaIydVS6K4FhWfE,2557
+sglang/srt/sampling/penaltylib/penalizers/min_new_tokens.py,sha256=XJZP0C4NFyXgcODbIWXxrgVEjmRgqLdZuVAtoN-LveY,3565
+sglang/srt/sampling/penaltylib/penalizers/presence_penalty.py,sha256=0PlANTrR959foTA3Nj5qBE7ndaOZgG-9X6LhzlmEUc8,2533
+sglang/srt/sampling/penaltylib/penalizers/repetition_penalty.py,sha256=v9jOgA0-I31WcrhIydiFbpy2ZJPLytFLGM98NRPd2sU,2820
+sglang/test/few_shot_gsm8k.py,sha256=uSHEPvUFbAgWKtaqxkhBpQrQV_SlTk0HN9FhjNLpL4g,3731
+sglang/test/run_eval.py,sha256=NWxeLWmInBgkCvC9Jr_QzF7GfAiBve3Gf1JQrEOlNlU,3899
+sglang/test/runners.py,sha256=ZoWhT1TDXfLBVdbivXx1KUu9dhPlGjL_xrP18WLzVLo,11404
+sglang/test/simple_eval_common.py,sha256=r0G-9QLycs2ax3RMc44T_61fzMxlpTzv6pececC7lyY,12379
+sglang/test/simple_eval_gpqa.py,sha256=8Xt9Bw05c7SZTYrCZgB68OZUqUbLo69ywiyx0bTvSUk,3220
+sglang/test/simple_eval_humaneval.py,sha256=7lTi841NT58smNOtRwCedrdX9IWWypdLkOtaQOBy-GI,5687
+sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWUpk,2550
+sglang/test/simple_eval_mgsm.py,sha256=wfbqJW9Rkc66vzq2fEMF6jchmoA8mw1OUiGU55cZ2B0,10261
+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=3-XKnppQdCNWjaJb6jwib5Z9OSpgKvH8SFLJbE4J9qI,17001
+sglang/test/test_utils.py,sha256=iBs07MBFxOidipTG1-s2hrCvcURFJVXo7gg10pzAQX8,17168
+sglang/test/srt/sampling/penaltylib/utils.py,sha256=-0p0rV-P4lNo7xAe3rQSBHTubc50a-DFyOQmLGAkgkQ,12515
+sglang-0.3.1.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+sglang-0.3.1.dist-info/METADATA,sha256=QKZQ7PjuK22x_QlQy1LqPX6y4zLgJJ9FPoNNSkw3cEk,38125
+sglang-0.3.1.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
+sglang-0.3.1.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
+sglang-0.3.1.dist-info/RECORD,,

{sglang-0.3.0.dist-info → sglang-0.3.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (74.1.1)
+Generator: setuptools (74.1.2)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

sglang-0.3.0.dist-info/RECORD

@@ -1,118 +0,0 @@
-sglang/__init__.py,sha256=T8MYdFfKFPZcgFKHMBpOCIlFbhjwmr77Nqm6mdE6bCY,1590
-sglang/api.py,sha256=pH4CjwOXUweL5MF1sIkFMddDxfnF7PyUxEHC5kvNVbI,6468
-sglang/bench_latency.py,sha256=F7jMfKqMf1XFKJgkpR_yE33VJpsIhSr_SOJeRbngkb0,16758
-sglang/bench_serving.py,sha256=J_mMwnmDn0Jt07mzdGAuYOxpockHPLYJFL-kwoaqASY,36527
-sglang/check_env.py,sha256=rGRABCgt-0SfUrow4px28b2P59aMn8eVTnN5eZc_a8s,5397
-sglang/global_config.py,sha256=nwOjUflwqLQySPUMvk8Hk63TIS6mknh_ODSW3CZ1rJw,1704
-sglang/launch_server.py,sha256=FODfO0DW546dh-u1qDlWtrhsmj6hxkarXXv3cIdgkj8,549
-sglang/launch_server_llavavid.py,sha256=xnpSILJxsrbvqkERav5P26bErCQnhoTFmoKeScJltUA,1034
-sglang/utils.py,sha256=zxHwQhVxW_lWf-IH0wUw_pBTRLHLPypdRiU5M4XosMM,9669
-sglang/version.py,sha256=VrXpHDu3erkzwl_WXrqINBm9xWkcyUy53IQOj042dOs,22
-sglang/lang/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sglang/lang/chat_template.py,sha256=uqI_I9zIKXGXg7-W-yjqvx1ZeS_TuwFCms6wkmC2QmY,13411
-sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
-sglang/lang/compiler.py,sha256=o1C6G3TzhjSlsH-doTPy5oiVehr57dxNTa5oZw5TTAI,7639
-sglang/lang/interpreter.py,sha256=AC3tNNDwYfiu87jCldBWXYpFicCv6NMPJACMFEfCXu4,30331
-sglang/lang/ir.py,sha256=W3UfZikcGeT86PDDjDjw-yNzrKY2e2UYO4DTatMCfm0,17704
-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=Q5HdiDtyBewQeoYH0kDtBRVL8KFiEPNq9dw7XmauHQ8,1985
-sglang/lang/backend/litellm.py,sha256=ugmL7sfUxkUHVbHtwNzHgdQAEd4UCjNQboFuE3KThcY,2450
-sglang/lang/backend/openai.py,sha256=qM7eVH_kMxnDd2rpxOH0v76KxtOJFlAwgLgWIKvFGCI,15060
-sglang/lang/backend/runtime_endpoint.py,sha256=hpezro0H6vG9KzLeKfYpPMwb4TaE0UanCIM0uG8Kdjw,9746
-sglang/lang/backend/vertexai.py,sha256=O-iBLD-y3vq80UxnrAoJri7bxpgd-_eakZ88Cf8bEGA,4855
-sglang/srt/conversation.py,sha256=2KDNe1suUPy6xqSkCx2xcO3pDPxTwqx5FaUxaqwCJ-M,19525
-sglang/srt/hf_transformers_utils.py,sha256=5UXJ-LdP92Sk_T843M9BHdnxRrcyiYfWH2IEg3dWgKI,6085
-sglang/srt/mm_utils.py,sha256=zox644S3IHUWmADdK4MnIbdTS2DWHOy0_Dq0gCU38QQ,12273
-sglang/srt/model_config.py,sha256=68QQ8iUWQHPv01RBeH23mvay6iJg9DWmCogC_vUgFLk,6371
-sglang/srt/server.py,sha256=yi8prs9_M0P0dOInrQLkHKiZ-oTigk_uzW8otEHImbU,19846
-sglang/srt/server_args.py,sha256=GiDyPWCvYA_98mSE9LuvUoEodo9gRnNPPIPn0nFkxUs,18259
-sglang/srt/utils.py,sha256=JJOlqRPbN_tSSNWj63syQpfz4v7hUwNvzWvOUpBh9SM,23746
-sglang/srt/configs/__init__.py,sha256=292SuEorST-lAq2Uvsv2M7yC28uYZlssVvRDsF-bZCQ,86
-sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
-sglang/srt/constrained/__init__.py,sha256=NLpZGj9RIx83ejDrM_pfaRtqGgaPq_ggJszPQENUJ2E,2037
-sglang/srt/constrained/base_tool_cache.py,sha256=5sazBMHHDpHMoqOjuY6itCxwTmIFCflIWEDXMtmrPVs,2006
-sglang/srt/constrained/fsm_cache.py,sha256=wigJs9PeTt-vYPJQEeUZwEKl6MFIfb5xy8uIg18bDbM,3132
-sglang/srt/constrained/jump_forward.py,sha256=LWRsmGPQcH6KT87wXwCRqtblU3pcAVCEzO0nWPxevs0,6636
-sglang/srt/layers/activation.py,sha256=JEXNTgqxoiU4N-gVm4XMjobhft4JKDcMrgTkfpsRUzM,4856
-sglang/srt/layers/decode_attention.py,sha256=TPD_608ZX9fQ_HDImifkxG_qcEYmimbEYY8lCBIjFuM,16628
-sglang/srt/layers/extend_attention.py,sha256=XIXm3p2cvKrDg10Po4qYGaEkXJOJBtCIhTB_lTyjAFE,14390
-sglang/srt/layers/layernorm.py,sha256=RXuS4UyksatqTF6lSK7VYyEiUEnBiNIBlEn8q4w84UA,3404
-sglang/srt/layers/logits_processor.py,sha256=Zx4eFAkFlThPrmz_-HuCN9SqGLanARm0wdZSVDyASAc,13085
-sglang/srt/layers/pooler.py,sha256=qNMG3Ycvt2yf9mk1Lcs-2K7oPeCuVeDYoHAxkMu9b_Q,1610
-sglang/srt/layers/prefill_attention.py,sha256=y7vdcuX8lMa9Qf_jQYNDvQO9PVCBQSs3hb5LV2DFgpU,5256
-sglang/srt/layers/radix_attention.py,sha256=o5a8r3XQ-oRwaxBlAgzJGv7p3dMbu0LrYsDc4uvpPgA,8338
-sglang/srt/layers/sampler.py,sha256=zPVa3PHc-tjDM_oP-1XFeHSRIErx844SLoe6MG8Qef0,6418
-sglang/srt/layers/fused_moe/__init__.py,sha256=bWCrDdOy2ANEXTb8CHYO63O3Iu3eZnn0PJbgl0z5vvE,75
-sglang/srt/layers/fused_moe/fused_moe.py,sha256=1WM2cObWXcFWtqh_utGJFPnrT344rORwuQ9hJDaH2s0,23104
-sglang/srt/layers/fused_moe/layer.py,sha256=GT3r2UPx_PAufJd0SUMOXyh76ymAeYDubd0SM0H71bo,20977
-sglang/srt/managers/controller_multi.py,sha256=z3rguY1YYlSvVqLjKuurgJW1h0dxwPgIdPCQdJsVzYs,6478
-sglang/srt/managers/controller_single.py,sha256=5brrZ8vZxjvrSJHWrm5H3qGEZShN4EROG5r1o3pSjps,5124
-sglang/srt/managers/detokenizer_manager.py,sha256=yQkL5gLomLiy1qc6e9HNz8hcj7JQFHm1AfIrzpXaWJE,6852
-sglang/srt/managers/io_struct.py,sha256=Bd91cydX9_960NNP2xngqK-lsIaDB3oMYd56QddN4_Q,10722
-sglang/srt/managers/policy_scheduler.py,sha256=7HNUxBKJE444s_bHcPpbnHCygsnH-NIXYNSC2q6mRmc,8584
-sglang/srt/managers/schedule_batch.py,sha256=i68O-e9I_gDlme96xSBDjA2xDF1p-XBKvJRiJ9CsgcY,26423
-sglang/srt/managers/tokenizer_manager.py,sha256=8aHR5h9nYZsfdZE80uBc9egDFOQgKvjxmp-30Ha4ELk,29463
-sglang/srt/managers/tp_worker.py,sha256=4UuaBLzV6NMsG4XEIcpa4xMcOKIFvTan51ynKz85HXg,36842
-sglang/srt/mem_cache/base_prefix_cache.py,sha256=qEQwEkG4E5rab2ZoTqcesf5pR_J4nV2jBxIHsBJHtIM,924
-sglang/srt/mem_cache/chunk_cache.py,sha256=CjZZYlqQzq7mYOiBMLWA5XNb6HIyh5lIMdY-K0OUZEc,2368
-sglang/srt/mem_cache/flush_cache.py,sha256=pTLKPRB17U6vl5RFJJvuJ4jCL2SyomgkUBNlkDpGRqo,978
-sglang/srt/mem_cache/memory_pool.py,sha256=4br3Ea2bfA-YsF_sPOVHlF2zQzYGd8fVaYTp197yZsE,7871
-sglang/srt/mem_cache/radix_cache.py,sha256=0AVr1BKKDOtTyybUkwxrz6PT8khDx-DpzgN5MgL27IE,10088
-sglang/srt/model_executor/cuda_graph_runner.py,sha256=4vIUqVQpnHNhwWrokMVmGM4Dp5JFPHyXIvpEQsi2pNU,12862
-sglang/srt/model_executor/forward_batch_info.py,sha256=fSLhatN8vCgxn0Mft9D-r0pNi3SN0EQSTJmgaOtrqJc,16471
-sglang/srt/model_executor/model_runner.py,sha256=93YCStmZfdZlY0r-GGIVi0Xw66VwF77dEtGVmQf1VfU,23893
-sglang/srt/models/chatglm.py,sha256=PPOaeqipbkcsTUhMPbLb1HItWgW7KntefUfjEoMSxUM,13585
-sglang/srt/models/commandr.py,sha256=k86ykwWOlxLGaBbGUoMSaXngUxCbMVRbY5AoMOWpbU8,14377
-sglang/srt/models/dbrx.py,sha256=goLJ9Yt-9vxkwhCUFBidvP41H_dYTFsvrMZ4xm4FqGA,14875
-sglang/srt/models/deepseek.py,sha256=aYP6HUgxQbhcQGQEF4vX0ronBF8AirqIFG98EQn0YzY,16220
-sglang/srt/models/deepseek_v2.py,sha256=Htw_HDju9huYU5gBu2dqq6bKVao-AsifxfkGl2xRx-8,28521
-sglang/srt/models/exaone.py,sha256=ZFr0G0WITxg3dDfV_-vWqZpK_wMmiZi4r0vOT0gO9V4,13301
-sglang/srt/models/gemma.py,sha256=Ya_u2lKPKAc9iHEsW_HAEfCDgYTbxUOCzBI0LDuoOYs,12489
-sglang/srt/models/gemma2.py,sha256=MCmzzRAAafEQuQj6aGtB-TF4jH0RWrXcOPxSz6LRsXs,15137
-sglang/srt/models/gpt_bigcode.py,sha256=HEhMRO1Y37JfZtP7mDp0MexWj5h6XT9rKvxorOMKoQA,10409
-sglang/srt/models/grok.py,sha256=ZcJ4E11rKh-xo4k_j-H1XRreJWWv8yii-bMYC1lO2R8,15143
-sglang/srt/models/internlm2.py,sha256=VtWATs2eLIqbadYXTPY_vycFIstVk4zg3kxycA9H0Qw,12416
-sglang/srt/models/llama.py,sha256=MfDnlVWoJUG9DxgGYPiwhoU-0ZeRbhp6UmBR2ZAJSNk,13402
-sglang/srt/models/llama_classification.py,sha256=oSeROs633Gnak8vrbnWnCWDxfgP_zmKGO1A_43ukEQ4,4029
-sglang/srt/models/llama_embedding.py,sha256=RI2mpYheP5WwhuTINU-6IrU61usuMyCK9h2zDEyLW4g,3458
-sglang/srt/models/llava.py,sha256=OXmlOVIjFnMRKGwLweYB1N-xlfpZlTlZpqhsbwUCY6Y,23471
-sglang/srt/models/llavavid.py,sha256=4R2t8BZJKN85IrTLsLFb4yZuKVI2Cwp7kY8AJ-nEVoE,12012
-sglang/srt/models/minicpm.py,sha256=7RZEJ2TCqBL1JmMFVJ3J9DmZHRw0q90st49Wkh-sdL4,14039
-sglang/srt/models/mistral.py,sha256=tiYoKjyYVzlQl52QUZ33odD2yCxj9dxcqln474VuZOw,744
-sglang/srt/models/mixtral.py,sha256=KIsvruhXNq3Fwrs4_YE7J6fx54ObfnMuRNxgScE3Bmo,13830
-sglang/srt/models/mixtral_quant.py,sha256=O_97UKDYZokFhIBnamWfw0HLhln9_BUk_KfQ-sQnd8s,14286
-sglang/srt/models/qwen.py,sha256=geK88AyEyPbbDvMHJNY8XMSNpsCeu8g9kxnKyiJBpK4,10168
-sglang/srt/models/qwen2.py,sha256=WGYy3wcRY3f8Drd9I8GblXfv0bbHluRKVhnnhEZf584,12654
-sglang/srt/models/qwen2_moe.py,sha256=b0gd42GBWyvDmUu8BZbD9ZJO_ExbXBLQZRvu61UuXOA,17086
-sglang/srt/models/stablelm.py,sha256=9feHoiDEXSIe0WCrt4AfWXqxliJwRvr8w4XSnk6ipSI,11573
-sglang/srt/models/yivl.py,sha256=B6MELthWIm5KdSzX3o2tbbpApY8XdjUdmcQSD4dQe_I,4835
-sglang/srt/openai_api/adapter.py,sha256=3EeqASZXogpUkOP4xj7Rg_LfOLiIMUrZ9uFdeAy_pcc,50144
-sglang/srt/openai_api/protocol.py,sha256=onhnCjXpXCysvx_dLgOEmXz5XHHYB1t772cvHcK1GlY,9538
-sglang/srt/sampling/sampling_batch_info.py,sha256=CIoD0SzHSWCe7Wc4jkJj5vIPHGnOdfbgkC6fG5KQxOw,7551
-sglang/srt/sampling/sampling_params.py,sha256=ggOXxafqfCD-xrGYcM57byLZ79CIeBP4AD5F44L_CW0,5635
-sglang/srt/sampling/penaltylib/__init__.py,sha256=5vQw0Y5DSzmsoFg1IdMIKLwFVhYZ5ArADHVBYbSmOec,513
-sglang/srt/sampling/penaltylib/orchestrator.py,sha256=WkTNeDhj9H9rtp2ZZeX6MS2sdKSGlLboE6FcuKrwUo0,10815
-sglang/srt/sampling/penaltylib/penalizers/frequency_penalty.py,sha256=IvYioX53Vq_ji-0Zhcz_r5mUa3T3GaIydVS6K4FhWfE,2557
-sglang/srt/sampling/penaltylib/penalizers/min_new_tokens.py,sha256=XJZP0C4NFyXgcODbIWXxrgVEjmRgqLdZuVAtoN-LveY,3565
-sglang/srt/sampling/penaltylib/penalizers/presence_penalty.py,sha256=0PlANTrR959foTA3Nj5qBE7ndaOZgG-9X6LhzlmEUc8,2533
-sglang/srt/sampling/penaltylib/penalizers/repetition_penalty.py,sha256=v9jOgA0-I31WcrhIydiFbpy2ZJPLytFLGM98NRPd2sU,2820
-sglang/test/run_eval.py,sha256=NWxeLWmInBgkCvC9Jr_QzF7GfAiBve3Gf1JQrEOlNlU,3899
-sglang/test/runners.py,sha256=7N2g4vyqN98o6F0Lem5LUNAlW9ShEVxZxZuzSjmc0i4,7688
-sglang/test/simple_eval_common.py,sha256=r0G-9QLycs2ax3RMc44T_61fzMxlpTzv6pececC7lyY,12379
-sglang/test/simple_eval_gpqa.py,sha256=8Xt9Bw05c7SZTYrCZgB68OZUqUbLo69ywiyx0bTvSUk,3220
-sglang/test/simple_eval_humaneval.py,sha256=7lTi841NT58smNOtRwCedrdX9IWWypdLkOtaQOBy-GI,5687
-sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWUpk,2550
-sglang/test/simple_eval_mgsm.py,sha256=wfbqJW9Rkc66vzq2fEMF6jchmoA8mw1OUiGU55cZ2B0,10261
-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=l21J8N91QTMO9TOvXPWNvPZVT0DgxYxOPHh1pOoFV_k,16927
-sglang/test/test_utils.py,sha256=3tt-BBv-lx7BT3whbVTMyRz6sh5jIbdBEbLZ08m2Ms8,15132
-sglang/test/srt/sampling/penaltylib/utils.py,sha256=-0p0rV-P4lNo7xAe3rQSBHTubc50a-DFyOQmLGAkgkQ,12515
-sglang-0.3.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-sglang-0.3.0.dist-info/METADATA,sha256=muukBuN4kq_4mCG_r_RFY94pQliDcVh-WuXNMApXoak,37383
-sglang-0.3.0.dist-info/WHEEL,sha256=uCRv0ZEik_232NlR4YDw4Pv3Ajt5bKvMH13NUU7hFuI,91
-sglang-0.3.0.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
-sglang-0.3.0.dist-info/RECORD,,