Liangsheng Yin b9fd178f1b Fix retraction + overlap (#1860) ...

Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>

2024-10-31 18:27:42 -07:00

..

models

Add new model: Gpt2 (#1833)

2024-10-29 17:52:33 -07:00

sampling/penaltylib

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

Llama-3.1-8B-Instruct.json

Support double sparsity (#1459)

2024-10-14 02:00:41 -07:00

run_suite.py

Fix memory leak for chunked prefill 2 (#1858)

2024-10-31 14:51:51 -07:00

test_bench_latency.py

Enable torch.compile for triton backend (#1422)

2024-09-14 15:38:37 -07:00

test_bench_serving.py

[Minor, Performance] Use torch.argmax for greedy sampling (#1589)

2024-10-06 13:15:05 -07:00

test_cache_report.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_chunked_prefill.py

Fix mixed chunked prefill (#1850)

2024-10-30 21:20:41 -07:00

test_create_kvindices.py

Organize Attention Backends (#1547)

2024-09-30 15:54:18 -07:00

test_data_parallelism.py

fix get_memory_pool_size deadlock for DP (#1830)

2024-10-28 23:07:14 -07:00

test_double_sparsity.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_embedding_openai_server.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_eval_accuracy_large_chunked_prefill.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_eval_accuracy_large_mixed_chunked_prefill.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_eval_accuracy_large.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_eval_accuracy_mini.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_json_constrained.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_large_max_new_tokens.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_matched_stop.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_mla_fp8.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_mla.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_models_from_modelscope.py

Improve process creation (#1534)

2024-09-29 02:36:12 -07:00

test_moe_eval_accuracy_large.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_nightly_gsm8k_eval.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_openai_server.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_overlap_schedule.py

Enhance the test case for chunked prefill (#1785)

2024-10-24 21:23:09 -07:00

test_pytorch_sampling_backend.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_radix_attention.py

Fix retraction + overlap (#1860)

2024-10-31 18:27:42 -07:00

test_retract_decode.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_server_args.py

Update vllm to 0.6.3 (#1711) (#1720)

2024-10-19 20:45:41 -07:00

test_skip_tokenizer_init.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_srt_endpoint.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_srt_engine.py

Support token ids in engine.generate (#1820)

2024-10-27 14:02:34 -07:00

test_torch_compile.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_torchao.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_triton_attention_backend.py

Fix Triton decode kernel & ut (#1819)

2024-10-27 10:54:38 -07:00

test_triton_attention_kernels.py

Fix Triton decode kernel & ut (#1819)

2024-10-27 10:54:38 -07:00

test_update_weights.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00

test_vision_openai_server.py

Add a watch dog thread (#1816)

2024-10-27 02:00:50 -07:00