…

..

ascend

…

configs

…

cpu

…

ep

…

models

support page size large than 64 for mamba radix cache with fix (#16768)

2026-01-09 13:28:37 +08:00

quant

…

xpu

…

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

…

experiment_runner.py

…

kv_cache_scales_llama3_1_8b.json

…

kv_cache_scales_llama3_8b.json

…

kv_cache_scales_qwen2_1_5b.json

…

parse_results.py

…

run_suite.py

…

test_bench_one_batch.py

…

test_bench_serving.py

[AMD] CI - add 2 pp test cases to performance-test-2-gpu-amd (#16514)

2026-01-06 23:52:46 -08:00

test_bench_typebaseddispatcher.py

…

test_bnb.py

…

test_deepseek_r1_mxfp4_8gpu.py

…

test_deepseek_v3_basic.py

…

test_deepseek_v3_cutedsl_4gpu.py

…

test_deepseek_v3_fp4_4gpu.py

[Tiny]Move deepseek fp4 cutlass moe test to per-commit test (#15565)

2025-12-21 18:08:07 -08:00

test_deepseek_v3_mtp.py

…

test_deepseek_v32_basic.py

…

test_deepseek_v32_mtp.py

…

test_disaggregation_different_tp.py

…

test_disaggregation_dp_attention.py

…

test_disaggregation_hybrid_attention.py

…

test_disaggregation_pp.py

…

test_embed_interpolate_unittest.py

…

test_epd_disaggregation.py

…

test_eval_accuracy_large.py

…

test_fp8_blockwise_gemm.py

…

test_gguf.py

…

test_gpt_oss_4gpu.py

…

test_gptqmodel_dynamic.py

…

test_llama31_fp4.py

fix b200 ci (#14786)

2025-12-09 23:08:41 -08:00

test_mistral_large3_basic.py

…

test_moe_eval_accuracy_large.py

…

test_multi_instance_release_memory_occupation.py

…

test_pp_single_node.py

…

test_prefill_delayer.py

…

test_profile_v2.py

…

test_quantization.py

…

test_release_memory_occupation.py

…

test_rope_rocm.py

…

test_type_based_dispatcher.py

…