hailin cc76bab27e first commit		2025-09-15 10:32:17 +08:00
..
ascend	first commit	2025-09-15 10:32:17 +08:00
configs	first commit	2025-09-15 10:32:17 +08:00
cpu	first commit	2025-09-15 10:32:17 +08:00
entrypoints/http_server	first commit	2025-09-15 10:32:17 +08:00
ep	first commit	2025-09-15 10:32:17 +08:00
hicache	first commit	2025-09-15 10:32:17 +08:00
lora	first commit	2025-09-15 10:32:17 +08:00
models	first commit	2025-09-15 10:32:17 +08:00
openai_server	first commit	2025-09-15 10:32:17 +08:00
quant	first commit	2025-09-15 10:32:17 +08:00
rl	first commit	2025-09-15 10:32:17 +08:00
double-sparsity-config-Llama-3.1-8B-Instruct.json	first commit	2025-09-15 10:32:17 +08:00
experiment_runner.py	first commit	2025-09-15 10:32:17 +08:00
kv_cache_scales_llama3_1_8b.json	first commit	2025-09-15 10:32:17 +08:00
kv_cache_scales_llama3_8b.json	first commit	2025-09-15 10:32:17 +08:00
kv_cache_scales_qwen2_1_5b.json	first commit	2025-09-15 10:32:17 +08:00
parse_results.py	first commit	2025-09-15 10:32:17 +08:00
run_suite.py	first commit	2025-09-15 10:32:17 +08:00
test_abort.py	first commit	2025-09-15 10:32:17 +08:00
test_bench_one_batch.py	first commit	2025-09-15 10:32:17 +08:00
test_bench_serving.py	first commit	2025-09-15 10:32:17 +08:00
test_bnb.py	first commit	2025-09-15 10:32:17 +08:00
test_chunked_prefill.py	first commit	2025-09-15 10:32:17 +08:00
test_cpp_radix_cache.py	first commit	2025-09-15 10:32:17 +08:00
test_cpu_graph.py	first commit	2025-09-15 10:32:17 +08:00
test_create_kvindices.py	first commit	2025-09-15 10:32:17 +08:00
test_custom_allreduce.py	first commit	2025-09-15 10:32:17 +08:00
test_data_parallelism.py	first commit	2025-09-15 10:32:17 +08:00
test_disaggregation.py	first commit	2025-09-15 10:32:17 +08:00
test_disaggregation_different_tp.py	first commit	2025-09-15 10:32:17 +08:00
test_disaggregation_pp.py	first commit	2025-09-15 10:32:17 +08:00
test_double_sparsity.py	first commit	2025-09-15 10:32:17 +08:00
test_dp_attention.py	first commit	2025-09-15 10:32:17 +08:00
test_eagle_infer_a.py	first commit	2025-09-15 10:32:17 +08:00
test_eagle_infer_b.py	first commit	2025-09-15 10:32:17 +08:00
test_ebnf_constrained.py	first commit	2025-09-15 10:32:17 +08:00
test_eval_accuracy_large.py	first commit	2025-09-15 10:32:17 +08:00
test_eval_fp8_accuracy.py	first commit	2025-09-15 10:32:17 +08:00
test_expert_distribution.py	first commit	2025-09-15 10:32:17 +08:00
test_expert_location_updater.py	first commit	2025-09-15 10:32:17 +08:00
test_fa3.py	first commit	2025-09-15 10:32:17 +08:00
test_fim_completion.py	first commit	2025-09-15 10:32:17 +08:00
test_flashmla.py	first commit	2025-09-15 10:32:17 +08:00
test_forward_split_prefill.py	first commit	2025-09-15 10:32:17 +08:00
test_full_deepseek_v3.py	first commit	2025-09-15 10:32:17 +08:00
test_function_call_parser.py	first commit	2025-09-15 10:32:17 +08:00
test_fused_moe.py	first commit	2025-09-15 10:32:17 +08:00
test_get_weights_by_name.py	first commit	2025-09-15 10:32:17 +08:00
test_gguf.py	first commit	2025-09-15 10:32:17 +08:00
test_gpt_oss_1gpu.py	first commit	2025-09-15 10:32:17 +08:00
test_gpt_oss_4gpu.py	first commit	2025-09-15 10:32:17 +08:00
test_gpt_oss_common.py	first commit	2025-09-15 10:32:17 +08:00
test_gptqmodel_dynamic.py	first commit	2025-09-15 10:32:17 +08:00
test_harmony_parser.py	first commit	2025-09-15 10:32:17 +08:00
test_health_check.py	first commit	2025-09-15 10:32:17 +08:00
test_hidden_states.py	first commit	2025-09-15 10:32:17 +08:00
test_hybrid_attn_backend.py	first commit	2025-09-15 10:32:17 +08:00
test_input_embeddings.py	first commit	2025-09-15 10:32:17 +08:00
test_intel_amx_attention_backend.py	first commit	2025-09-15 10:32:17 +08:00
test_io_struct.py	first commit	2025-09-15 10:32:17 +08:00
test_jinja_template_utils.py	first commit	2025-09-15 10:32:17 +08:00
test_kv_events.py	first commit	2025-09-15 10:32:17 +08:00
test_local_attn.py	first commit	2025-09-15 10:32:17 +08:00
test_metrics.py	first commit	2025-09-15 10:32:17 +08:00
test_metrics_utils.py	first commit	2025-09-15 10:32:17 +08:00
test_mla.py	first commit	2025-09-15 10:32:17 +08:00
test_mla_deepseek_v3.py	first commit	2025-09-15 10:32:17 +08:00
test_mla_flashinfer.py	first commit	2025-09-15 10:32:17 +08:00
test_mla_fp8.py	first commit	2025-09-15 10:32:17 +08:00
test_mla_int8_deepseek_v3.py	first commit	2025-09-15 10:32:17 +08:00
test_mla_tp.py	first commit	2025-09-15 10:32:17 +08:00
test_modelopt.py	first commit	2025-09-15 10:32:17 +08:00
test_modelopt_fp8kvcache.py	first commit	2025-09-15 10:32:17 +08:00
test_models_from_modelscope.py	first commit	2025-09-15 10:32:17 +08:00
test_moe_eval_accuracy_large.py	first commit	2025-09-15 10:32:17 +08:00
test_mscclpp.py	first commit	2025-09-15 10:32:17 +08:00
test_multi_instance_release_memory_occupation.py	first commit	2025-09-15 10:32:17 +08:00
test_multi_tokenizer.py	first commit	2025-09-15 10:32:17 +08:00
test_nightly_gsm8k_eval.py	first commit	2025-09-15 10:32:17 +08:00
test_nightly_gsm8k_eval_amd.py	first commit	2025-09-15 10:32:17 +08:00
test_no_chunked_prefill.py	first commit	2025-09-15 10:32:17 +08:00
test_no_overlap_scheduler.py	first commit	2025-09-15 10:32:17 +08:00
test_original_logprobs.py	first commit	2025-09-15 10:32:17 +08:00
test_page_size.py	first commit	2025-09-15 10:32:17 +08:00
test_patch_torch.py	first commit	2025-09-15 10:32:17 +08:00
test_penalty.py	first commit	2025-09-15 10:32:17 +08:00
test_pp_single_node.py	first commit	2025-09-15 10:32:17 +08:00
test_pytorch_sampling_backend.py	first commit	2025-09-15 10:32:17 +08:00
test_quick_allreduce.py	first commit	2025-09-15 10:32:17 +08:00
test_radix_attention.py	first commit	2025-09-15 10:32:17 +08:00
test_reasoning_parser.py	first commit	2025-09-15 10:32:17 +08:00
test_regex_constrained.py	first commit	2025-09-15 10:32:17 +08:00
test_release_memory_occupation.py	first commit	2025-09-15 10:32:17 +08:00
test_request_queue_validation.py	first commit	2025-09-15 10:32:17 +08:00
test_retract_decode.py	first commit	2025-09-15 10:32:17 +08:00
test_rope_rocm.py	first commit	2025-09-15 10:32:17 +08:00
test_sagemaker_server.py	first commit	2025-09-15 10:32:17 +08:00
test_schedule_policy.py	first commit	2025-09-15 10:32:17 +08:00
test_score_api.py	first commit	2025-09-15 10:32:17 +08:00
test_server_args.py	first commit	2025-09-15 10:32:17 +08:00
test_session_control.py	first commit	2025-09-15 10:32:17 +08:00
test_skip_tokenizer_init.py	first commit	2025-09-15 10:32:17 +08:00
test_srt_endpoint.py	first commit	2025-09-15 10:32:17 +08:00
test_srt_engine.py	first commit	2025-09-15 10:32:17 +08:00
test_srt_engine_with_quant_args.py	first commit	2025-09-15 10:32:17 +08:00
test_standalone_speculative_decoding.py	first commit	2025-09-15 10:32:17 +08:00
test_start_profile.py	first commit	2025-09-15 10:32:17 +08:00
test_swa_unittest.py	first commit	2025-09-15 10:32:17 +08:00
test_tokenizer_batch_encode.py	first commit	2025-09-15 10:32:17 +08:00
test_torch_compile.py	first commit	2025-09-15 10:32:17 +08:00
test_torch_compile_moe.py	first commit	2025-09-15 10:32:17 +08:00
test_torch_native_attention_backend.py	first commit	2025-09-15 10:32:17 +08:00
test_torch_tp.py	first commit	2025-09-15 10:32:17 +08:00
test_torchao.py	first commit	2025-09-15 10:32:17 +08:00
test_triton_attention_backend.py	first commit	2025-09-15 10:32:17 +08:00
test_triton_attention_kernels.py	first commit	2025-09-15 10:32:17 +08:00
test_triton_attention_rocm_mla.py	first commit	2025-09-15 10:32:17 +08:00
test_triton_fused_moe.py	first commit	2025-09-15 10:32:17 +08:00
test_triton_moe_channel_fp8_kernel.py	first commit	2025-09-15 10:32:17 +08:00
test_triton_moe_wna16.py	first commit	2025-09-15 10:32:17 +08:00
test_triton_sliding_window.py	first commit	2025-09-15 10:32:17 +08:00
test_two_batch_overlap.py	first commit	2025-09-15 10:32:17 +08:00
test_utils_update_weights.py	first commit	2025-09-15 10:32:17 +08:00
test_vertex_endpoint.py	first commit	2025-09-15 10:32:17 +08:00
test_vision_chunked_prefill.py	first commit	2025-09-15 10:32:17 +08:00
test_vision_openai_server_a.py	first commit	2025-09-15 10:32:17 +08:00
test_vision_openai_server_b.py	first commit	2025-09-15 10:32:17 +08:00
test_vision_openai_server_common.py	first commit	2025-09-15 10:32:17 +08:00
test_vllm_dependency.py	first commit	2025-09-15 10:32:17 +08:00
test_vlm_accuracy.py	first commit	2025-09-15 10:32:17 +08:00
test_vlm_input_format.py	first commit	2025-09-15 10:32:17 +08:00
test_wave_attention_backend.py	first commit	2025-09-15 10:32:17 +08:00
test_wave_attention_kernels.py	first commit	2025-09-15 10:32:17 +08:00
test_weight_version.py	first commit	2025-09-15 10:32:17 +08:00