Aurick Qiao c6cb0c9649 [Session] Add streaming mode with SessionAwareCache fast path (#19171) ...

Co-authored-by: hnyls2002 <lsyincs@gmail.com>

2026-02-27 16:31:08 -08:00

..

ascend

…

cpu

…

debug_utils

…

entrypoints/http_server

…

ep

[4/N] (Elastic EP) Back up Expert Weights in DRAM (#17374)

2026-02-27 15:59:13 +08:00

hicache

[Benchmark] Remove re-exports from bench_serving.py (#19130)

2026-02-21 14:30:30 -08:00

kv_transfer

…

lang_frontend

…

layers

…

lora

…

models

…

nightly

[VLM] Introduce FlashInfer CUDNN Prefill as ViT Backend (#19003)

2026-02-24 19:49:22 +08:00

openai_server/features

…

piecewise_cudagraph

[CI] feat: add early exit to wait_for_server when process dies (#18602)

2026-02-13 16:46:09 -08:00

quant

…

vlm

[FEAT] Add Anthropic compatible API endpoint (#18630)

2026-02-21 19:37:38 +08:00

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

[CI] feat: add early exit to wait_for_server when process dies (#18602)

2026-02-13 16:46:09 -08:00

test_mscclpp.py

…

test_quick_allreduce.py

…

test_sagemaker_server.py

…

test_schedule_policy.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

Refactor: observability code cleanup (#17862)

2026-02-24 18:07:29 -08:00

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

update pre-commit config (#18860)

2026-02-16 00:18:31 +08:00

test_wave_attention_backend.py

…

test_weight_validation.py

…

test_weight_version.py

…