LICENSE
README.md
pyproject.toml
sglang/__init__.py
sglang/api.py
sglang/bench_latency.py
sglang/bench_offline_throughput.py
sglang/bench_one_batch.py
sglang/bench_one_batch_server.py
sglang/bench_serving.py
sglang/check_env.py
sglang/global_config.py
sglang/launch_server.py
sglang/llama3_eval.py
sglang/utils.py
sglang/version.py
sglang.egg-info/PKG-INFO
sglang.egg-info/SOURCES.txt
sglang.egg-info/dependency_links.txt
sglang.egg-info/requires.txt
sglang.egg-info/top_level.txt
sglang/lang/__init__.py
sglang/lang/chat_template.py
sglang/lang/choices.py
sglang/lang/compiler.py
sglang/lang/interpreter.py
sglang/lang/ir.py
sglang/lang/tracer.py
sglang/lang/backend/__init__.py
sglang/lang/backend/anthropic.py
sglang/lang/backend/base_backend.py
sglang/lang/backend/litellm.py
sglang/lang/backend/openai.py
sglang/lang/backend/runtime_endpoint.py
sglang/lang/backend/vertexai.py
sglang/srt/_custom_ops.py
sglang/srt/aio_rwlock.py
sglang/srt/conversation.py
sglang/srt/function_call_parser.py
sglang/srt/hf_transformers_utils.py
sglang/srt/mm_utils.py
sglang/srt/model_parallel.py
sglang/srt/server.py
sglang/srt/server_args.py
sglang/srt/torch_memory_saver_adapter.py
sglang/srt/utils.py
sglang/srt/configs/__init__.py
sglang/srt/configs/chatglm.py
sglang/srt/configs/dbrx.py
sglang/srt/configs/device_config.py
sglang/srt/configs/exaone.py
sglang/srt/configs/load_config.py
sglang/srt/configs/model_config.py
sglang/srt/configs/qwen2vl.py
sglang/srt/constrained/base_grammar_backend.py
sglang/srt/constrained/outlines_backend.py
sglang/srt/constrained/outlines_jump_forward.py
sglang/srt/constrained/xgrammar_backend.py
sglang/srt/distributed/__init__.py
sglang/srt/distributed/communication_op.py
sglang/srt/distributed/parallel_state.py
sglang/srt/distributed/utils.py
sglang/srt/distributed/device_communicators/cuda_wrapper.py
sglang/srt/distributed/device_communicators/custom_all_reduce.py
sglang/srt/distributed/device_communicators/custom_all_reduce_utils.py
sglang/srt/distributed/device_communicators/hpu_communicator.py
sglang/srt/distributed/device_communicators/pynccl.py
sglang/srt/distributed/device_communicators/pynccl_wrapper.py
sglang/srt/distributed/device_communicators/shm_broadcast.py
sglang/srt/distributed/device_communicators/xpu_communicator.py
sglang/srt/entrypoints/engine.py
sglang/srt/entrypoints/http_server.py
sglang/srt/layers/activation.py
sglang/srt/layers/custom_op_util.py
sglang/srt/layers/dp_attention.py
sglang/srt/layers/layernorm.py
sglang/srt/layers/linear.py
sglang/srt/layers/logits_processor.py
sglang/srt/layers/parameter.py
sglang/srt/layers/pooler.py
sglang/srt/layers/radix_attention.py
sglang/srt/layers/rotary_embedding.py
sglang/srt/layers/sampler.py
sglang/srt/layers/torchao_utils.py
sglang/srt/layers/vocab_parallel_embedding.py
sglang/srt/layers/attention/__init__.py
sglang/srt/layers/attention/double_sparsity_backend.py
sglang/srt/layers/attention/flashinfer_backend.py
sglang/srt/layers/attention/torch_native_backend.py
sglang/srt/layers/attention/triton_backend.py
sglang/srt/layers/attention/vision.py
sglang/srt/layers/attention/triton_ops/decode_attention.py
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py
sglang/srt/layers/attention/triton_ops/extend_attention.py
sglang/srt/layers/attention/triton_ops/prefill_attention.py
sglang/srt/layers/moe/fused_moe_native.py
sglang/srt/layers/moe/topk.py
sglang/srt/layers/moe/ep_moe/__init__.py
sglang/srt/layers/moe/ep_moe/kernels.py
sglang/srt/layers/moe/ep_moe/layer.py
sglang/srt/layers/moe/fused_moe_triton/__init__.py
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py
sglang/srt/layers/moe/fused_moe_triton/layer.py
sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_H200.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=2560,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=2560,device_name=NVIDIA_H200.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=320,device_name=NVIDIA_H200.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=640,device_name=NVIDIA_H200.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=14336,device_name=NVIDIA_H200.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=1792,device_name=NVIDIA_H200.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=2048,device_name=NVIDIA_H200.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_H200.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=3584,device_name=NVIDIA_L40S.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=4096,device_name=NVIDIA_H200.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=7168,device_name=NVIDIA_H200.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
sglang/srt/layers/quantization/__init__.py
sglang/srt/layers/quantization/base_config.py
sglang/srt/layers/quantization/fp8.py
sglang/srt/layers/quantization/fp8_kernel.py
sglang/srt/layers/quantization/fp8_utils.py
sglang/srt/layers/quantization/int8_kernel.py
sglang/srt/layers/quantization/modelopt_quant.py
sglang/srt/layers/quantization/w8a8_int8.py
sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=36864,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
sglang/srt/lora/lora.py
sglang/srt/lora/lora_config.py
sglang/srt/lora/lora_manager.py
sglang/srt/managers/cache_controller.py
sglang/srt/managers/configure_logging.py
sglang/srt/managers/data_parallel_controller.py
sglang/srt/managers/detokenizer_manager.py
sglang/srt/managers/image_processor.py
sglang/srt/managers/io_struct.py
sglang/srt/managers/schedule_batch.py
sglang/srt/managers/schedule_policy.py
sglang/srt/managers/scheduler.py
sglang/srt/managers/session_controller.py
sglang/srt/managers/tokenizer_manager.py
sglang/srt/managers/tp_worker.py
sglang/srt/managers/tp_worker_overlap_thread.py
sglang/srt/managers/utils.py
sglang/srt/mem_cache/base_prefix_cache.py
sglang/srt/mem_cache/chunk_cache.py
sglang/srt/mem_cache/flush_cache.py
sglang/srt/mem_cache/memory_pool.py
sglang/srt/mem_cache/radix_cache.py
sglang/srt/metrics/collector.py
sglang/srt/metrics/func_timer.py
sglang/srt/model_executor/cuda_graph_runner.py
sglang/srt/model_executor/forward_batch_info.py
sglang/srt/model_executor/model_runner.py
sglang/srt/model_loader/__init__.py
sglang/srt/model_loader/loader.py
sglang/srt/model_loader/utils.py
sglang/srt/model_loader/weight_utils.py
sglang/srt/models/baichuan.py
sglang/srt/models/chatglm.py
sglang/srt/models/commandr.py
sglang/srt/models/dbrx.py
sglang/srt/models/deepseek.py
sglang/srt/models/deepseek_v2.py
sglang/srt/models/exaone.py
sglang/srt/models/gemma.py
sglang/srt/models/gemma2.py
sglang/srt/models/gemma2_reward.py
sglang/srt/models/gpt2.py
sglang/srt/models/gpt_bigcode.py
sglang/srt/models/granite.py
sglang/srt/models/grok.py
sglang/srt/models/internlm2.py
sglang/srt/models/internlm2_reward.py
sglang/srt/models/llama.py
sglang/srt/models/llama_classification.py
sglang/srt/models/llama_eagle.py
sglang/srt/models/llama_embedding.py
sglang/srt/models/llama_reward.py
sglang/srt/models/llava.py
sglang/srt/models/llavavid.py
sglang/srt/models/minicpm.py
sglang/srt/models/minicpm3.py
sglang/srt/models/minicpmv.py
sglang/srt/models/mistral.py
sglang/srt/models/mixtral.py
sglang/srt/models/mixtral_quant.py
sglang/srt/models/mllama.py
sglang/srt/models/olmo.py
sglang/srt/models/olmo2.py
sglang/srt/models/olmoe.py
sglang/srt/models/phi3_small.py
sglang/srt/models/qwen.py
sglang/srt/models/qwen2.py
sglang/srt/models/qwen2_eagle.py
sglang/srt/models/qwen2_moe.py
sglang/srt/models/qwen2_vl.py
sglang/srt/models/registry.py
sglang/srt/models/stablelm.py
sglang/srt/models/torch_native_llama.py
sglang/srt/models/xverse.py
sglang/srt/models/xverse_moe.py
sglang/srt/models/yivl.py
sglang/srt/openai_api/adapter.py
sglang/srt/openai_api/protocol.py
sglang/srt/sampling/custom_logit_processor.py
sglang/srt/sampling/sampling_batch_info.py
sglang/srt/sampling/sampling_params.py
sglang/srt/sampling/penaltylib/__init__.py
sglang/srt/sampling/penaltylib/orchestrator.py
sglang/srt/sampling/penaltylib/penalizers/frequency_penalty.py
sglang/srt/sampling/penaltylib/penalizers/min_new_tokens.py
sglang/srt/sampling/penaltylib/penalizers/presence_penalty.py
sglang/srt/sampling/penaltylib/penalizers/repetition_penalty.py
sglang/srt/speculative/build_eagle_tree.py
sglang/srt/speculative/eagle_utils.py
sglang/srt/speculative/eagle_worker.py
sglang/srt/speculative/spec_info.py
sglang/test/few_shot_gsm8k.py
sglang/test/few_shot_gsm8k_engine.py
sglang/test/run_eval.py
sglang/test/runners.py
sglang/test/simple_eval_common.py
sglang/test/simple_eval_gpqa.py
sglang/test/simple_eval_humaneval.py
sglang/test/simple_eval_math.py
sglang/test/simple_eval_mgsm.py
sglang/test/simple_eval_mmlu.py
sglang/test/test_activation.py
sglang/test/test_block_fp8.py
sglang/test/test_layernorm.py
sglang/test/test_programs.py
sglang/test/test_utils.py
sglang/test/srt/sampling/penaltylib/utils.py