hailin 466c38a2d4 first commit		2025-05-27 11:42:20 +08:00
..
configs	first commit	2025-05-27 11:42:20 +08:00
models	first commit	2025-05-27 11:42:20 +08:00
double-sparsity-config-Llama-3.1-8B-Instruct.json	first commit	2025-05-27 11:42:20 +08:00
experiment_runner.py	first commit	2025-05-27 11:42:20 +08:00
kv_cache_scales_llama3_1_8b.json	first commit	2025-05-27 11:42:20 +08:00
kv_cache_scales_llama3_8b.json	first commit	2025-05-27 11:42:20 +08:00
kv_cache_scales_qwen2_1_5b.json	first commit	2025-05-27 11:42:20 +08:00
run_suite.py	first commit	2025-05-27 11:42:20 +08:00
test_abort.py	first commit	2025-05-27 11:42:20 +08:00
test_awq.py	first commit	2025-05-27 11:42:20 +08:00
test_bench_one_batch.py	first commit	2025-05-27 11:42:20 +08:00
test_bench_serving.py	first commit	2025-05-27 11:42:20 +08:00
test_block_int8.py	first commit	2025-05-27 11:42:20 +08:00
test_cache_report.py	first commit	2025-05-27 11:42:20 +08:00
test_chunked_prefill.py	first commit	2025-05-27 11:42:20 +08:00
test_create_kvindices.py	first commit	2025-05-27 11:42:20 +08:00
test_custom_allreduce.py	first commit	2025-05-27 11:42:20 +08:00
test_data_parallelism.py	first commit	2025-05-27 11:42:20 +08:00
test_double_sparsity.py	first commit	2025-05-27 11:42:20 +08:00
test_dp_attention.py	first commit	2025-05-27 11:42:20 +08:00
test_eagle_infer.py	first commit	2025-05-27 11:42:20 +08:00
test_ebnf_constrained.py	first commit	2025-05-27 11:42:20 +08:00
test_embedding_openai_server.py	first commit	2025-05-27 11:42:20 +08:00
test_eval_accuracy_large.py	first commit	2025-05-27 11:42:20 +08:00
test_eval_fp8_accuracy.py	first commit	2025-05-27 11:42:20 +08:00
test_expert_distribution.py	first commit	2025-05-27 11:42:20 +08:00
test_fim_completion.py	first commit	2025-05-27 11:42:20 +08:00
test_fp8_kernel.py	first commit	2025-05-27 11:42:20 +08:00
test_fp8_kvcache.py	first commit	2025-05-27 11:42:20 +08:00
test_function_calling.py	first commit	2025-05-27 11:42:20 +08:00
test_fused_moe.py	first commit	2025-05-27 11:42:20 +08:00
test_get_weights_by_name.py	first commit	2025-05-27 11:42:20 +08:00
test_gguf.py	first commit	2025-05-27 11:42:20 +08:00
test_gptqmodel_dynamic.py	first commit	2025-05-27 11:42:20 +08:00
test_health_check.py	first commit	2025-05-27 11:42:20 +08:00
test_hicache.py	first commit	2025-05-27 11:42:20 +08:00
test_hicache_mla.py	first commit	2025-05-27 11:42:20 +08:00
test_hidden_states.py	first commit	2025-05-27 11:42:20 +08:00
test_input_embeddings.py	first commit	2025-05-27 11:42:20 +08:00
test_int8_kernel.py	first commit	2025-05-27 11:42:20 +08:00
test_json_constrained.py	first commit	2025-05-27 11:42:20 +08:00
test_large_max_new_tokens.py	first commit	2025-05-27 11:42:20 +08:00
test_matched_stop.py	first commit	2025-05-27 11:42:20 +08:00
test_metrics.py	first commit	2025-05-27 11:42:20 +08:00
test_mla.py	first commit	2025-05-27 11:42:20 +08:00
test_mla_deepseek_v3.py	first commit	2025-05-27 11:42:20 +08:00
test_mla_flashinfer.py	first commit	2025-05-27 11:42:20 +08:00
test_mla_fp8.py	first commit	2025-05-27 11:42:20 +08:00
test_mla_int8_deepseek_v3.py	first commit	2025-05-27 11:42:20 +08:00
test_mla_tp.py	first commit	2025-05-27 11:42:20 +08:00
test_modelopt_fp8kvcache.py	first commit	2025-05-27 11:42:20 +08:00
test_models_from_modelscope.py	first commit	2025-05-27 11:42:20 +08:00
test_moe_deepep.py	first commit	2025-05-27 11:42:20 +08:00
test_moe_ep.py	first commit	2025-05-27 11:42:20 +08:00
test_moe_eval_accuracy_large.py	first commit	2025-05-27 11:42:20 +08:00
test_nightly_gsm8k_eval.py	first commit	2025-05-27 11:42:20 +08:00
test_nightly_human_eval.py	first commit	2025-05-27 11:42:20 +08:00
test_nightly_math_eval.py	first commit	2025-05-27 11:42:20 +08:00
test_no_chunked_prefill.py	first commit	2025-05-27 11:42:20 +08:00
test_no_overlap_scheduler.py	first commit	2025-05-27 11:42:20 +08:00
test_openai_server.py	first commit	2025-05-27 11:42:20 +08:00
test_page_size.py	first commit	2025-05-27 11:42:20 +08:00
test_patch_torch.py	first commit	2025-05-27 11:42:20 +08:00
test_penalty.py	first commit	2025-05-27 11:42:20 +08:00
test_pytorch_sampling_backend.py	first commit	2025-05-27 11:42:20 +08:00
test_radix_attention.py	first commit	2025-05-27 11:42:20 +08:00
test_reasoning_content.py	first commit	2025-05-27 11:42:20 +08:00
test_regex_constrained.py	first commit	2025-05-27 11:42:20 +08:00
test_release_memory_occupation.py	first commit	2025-05-27 11:42:20 +08:00
test_request_length_validation.py	first commit	2025-05-27 11:42:20 +08:00
test_retract_decode.py	first commit	2025-05-27 11:42:20 +08:00
test_sagemaker_server.py	first commit	2025-05-27 11:42:20 +08:00
test_schedule_policy.py	first commit	2025-05-27 11:42:20 +08:00
test_server_args.py	first commit	2025-05-27 11:42:20 +08:00
test_session_control.py	first commit	2025-05-27 11:42:20 +08:00
test_skip_tokenizer_init.py	first commit	2025-05-27 11:42:20 +08:00
test_srt_endpoint.py	first commit	2025-05-27 11:42:20 +08:00
test_srt_engine.py	first commit	2025-05-27 11:42:20 +08:00
test_srt_engine_with_quant_args.py	first commit	2025-05-27 11:42:20 +08:00
test_torch_compile.py	first commit	2025-05-27 11:42:20 +08:00
test_torch_compile_moe.py	first commit	2025-05-27 11:42:20 +08:00
test_torch_native_attention_backend.py	first commit	2025-05-27 11:42:20 +08:00
test_torch_tp.py	first commit	2025-05-27 11:42:20 +08:00
test_torchao.py	first commit	2025-05-27 11:42:20 +08:00
test_triton_attention_backend.py	first commit	2025-05-27 11:42:20 +08:00
test_triton_attention_kernels.py	first commit	2025-05-27 11:42:20 +08:00
test_triton_attention_rocm_mla.py	first commit	2025-05-27 11:42:20 +08:00
test_update_weights_from_disk.py	first commit	2025-05-27 11:42:20 +08:00
test_update_weights_from_distributed.py	first commit	2025-05-27 11:42:20 +08:00
test_update_weights_from_tensor.py	first commit	2025-05-27 11:42:20 +08:00
test_verl_engine.py	first commit	2025-05-27 11:42:20 +08:00
test_vertex_endpoint.py	first commit	2025-05-27 11:42:20 +08:00
test_vision_chunked_prefill.py	first commit	2025-05-27 11:42:20 +08:00
test_vision_openai_server.py	first commit	2025-05-27 11:42:20 +08:00
test_vllm_dependency.py	first commit	2025-05-27 11:42:20 +08:00
test_vlm_accuracy.py	first commit	2025-05-27 11:42:20 +08:00
test_w8a8_quantization.py	first commit	2025-05-27 11:42:20 +08:00