Chang Su a8ccacc8b8 [Frontend] Fix request length check and add option to disallow auto truncation in scheduler (#2876)

2025-01-16 14:51:19 -08:00

..

configs

…

models

…

sampling/penaltylib

…

double-sparsity-config-Llama-3.1-8B-Instruct.json

…

experiment_runner.py

…

kv_cache_scales_llama3_1_8b.json

Support FP8 E4M3 KV Cache (#2786)

2025-01-12 21:17:11 -08:00

run_suite.py

[Frontend] Fix request length check and add option to disallow auto truncation in scheduler (#2876)

2025-01-16 14:51:19 -08:00

test_abort.py

…

test_bench_one_batch.py

…

test_bench_serving.py

…

test_cache_report.py

…

test_chunked_prefill.py

…

test_create_kvindices.py

…

test_custom_allreduce.py

adapt custom allreduce for tensorrt llm (#2511)

2025-01-16 04:57:35 +08:00

test_data_parallelism.py

…

test_double_sparsity.py

…

test_dp_attention.py

…

test_eagle_infer.py

[Eagle2] Fix multiple concurrent request crashes (#2730)

2025-01-10 14:00:43 -08:00

test_ebnf_constrained.py

…

test_embedding_openai_server.py

…

test_eval_accuracy_large_chunked_prefill.py

…

test_eval_accuracy_large_mixed_chunked_prefill.py

…

test_eval_accuracy_large.py

…

test_eval_accuracy_mini.py

…

test_fp8_kvcache.py

Support FP8 E4M3 KV Cache (#2786)

2025-01-12 21:17:11 -08:00

test_fused_moe.py

…

test_get_weights_by_name.py

…

test_gguf.py

…

test_input_embeddings.py

…

test_json_constrained.py

…

test_large_max_new_tokens.py

…

test_matched_stop.py

…

test_metrics.py

Collect more metrics: num_requests_total (#2859)

2025-01-13 03:57:39 -08:00

test_mla_fp8.py

Use only one GPU for MLA CI tests (#2858)

2025-01-13 03:55:33 -08:00

test_mla.py

Use only one GPU for MLA CI tests (#2858)

2025-01-13 03:55:33 -08:00

test_models_from_modelscope.py

…

test_moe_ep.py

Improve benchmark scripts and error message printing (#2922)

2025-01-16 06:24:31 -08:00

test_moe_eval_accuracy_large.py

Fix linear.py and improve weight loading (#2851)

2025-01-13 01:39:14 -08:00

test_nightly_gsm8k_eval.py

Update threshold in test_nightly_gsm8k_eval.py (#2836)

2025-01-10 20:37:34 -08:00

test_nightly_human_eval.py

Fix nightly accuracy tests (#2780)

2025-01-07 21:02:35 -08:00

test_nightly_math_eval.py

…

test_no_chunked_prefill.py

…

test_no_overlap_scheduler.py

…

test_openai_server.py

[Bugfix] Fix embedding model hangs with --enable-metrics (#2822)

2025-01-10 13:14:51 -08:00

test_pytorch_sampling_backend.py

…

test_radix_attention.py

…

test_release_memory_occupation.py

CUDA-graph-compatible releasing and resuming KV cache and model weight memory (#2630)

2025-01-13 11:38:51 -08:00

test_request_length_validation.py

[Frontend] Fix request length check and add option to disallow auto truncation in scheduler (#2876)

2025-01-16 14:51:19 -08:00

test_retract_decode.py

…

test_schedule_policy.py

…

test_server_args.py

…

test_session_control.py

…

test_skip_tokenizer_init.py

Improve: Token-In Token-Out Usage for RLHF (#2843)

2025-01-11 15:14:26 -08:00

test_srt_endpoint.py

…

test_srt_engine_with_quant_args.py

…

test_srt_engine.py

…

test_torch_compile_moe.py

…

test_torch_compile.py

…

test_torch_native_attention_backend.py

…

test_torch_tp.py

…

test_torchao.py

…

test_triton_attention_backend.py

Fix test and benchmark scripts (#2598)

2024-12-26 07:56:26 -08:00

test_triton_attention_kernels.py

…

test_update_weights_from_disk.py

…

test_update_weights_from_distributed.py

…

test_update_weights_from_tensor.py

…

test_vision_chunked_prefill.py

…

test_vision_openai_server.py

…

test_w8a8_quantization.py

Add ut for w8a8 int8 quantization (#2897)

2025-01-15 18:29:14 +08:00