BingjiaWangandabing 760ae933bb optimize get_topk_ragged by fusing get k and k_scale triton kernel (#16043) ...

Co-authored-by: abing <wangbingjia.wbj@alibaba-inc.com>

2026-02-04 19:59:41 +08:00

..

ascend

[NPU] [CI] temporarily disable mtp test (#17614)

2026-01-23 15:17:31 +08:00

cpu

…

debug_utils

…

entrypoints/http_server

…

ep

…

hicache

…

kv_transfer

…

lang_frontend

…

layers

optimize get_topk_ragged by fusing get k and k_scale triton kernel (#16043)

2026-02-04 19:59:41 +08:00

lora

…

models

…

nightly

…

openai_server/features

…

piecewise_cudagraph

…

quant

…

test_async_dynamic_batch_tokenizer.py

…

test_async_mm_data_processor.py

…

test_config_integration.py

…

test_custom_allreduce.py

…

test_deepseek_chat_templates.py

…

test_double_sparsity.py

…

test_expert_distribution.py

…

test_expert_location_updater.py

…

test_fim_completion.py

…

test_forward_split_prefill.py

…

test_get_weights_by_name.py

…

test_health_check.py

…

test_kv_events.py

…

test_logprobs.py

…

test_mla_tp.py

…

test_modelopt_fp8kvcache.py

…

test_modelopt.py

…

test_models_from_modelscope.py

…

test_mori_transfer_engine_e2e.py

…

test_mscclpp.py

…

test_quick_allreduce.py

…

test_sagemaker_server.py

…

test_schedule_policy.py

…

test_session_control.py

…

test_srt_engine_with_quant_args.py

…

test_tokenizer_batch_encode.py

…

test_tokenizer_manager.py

…

test_torch_flex_attention_backend.py

…

test_torch_tp.py

…

test_tracing.py

…

test_triton_attention_rocm_mla.py

…

test_triton_moe_wna16.py

…

test_trtllm_fp8_kv_kernel.py

…

test_two_batch_overlap.py

…

test_vertex_endpoint.py

…

test_vlm_accuracy.py

…

test_wave_attention_backend.py

…

test_weight_validation.py

…

test_weight_version.py

…