QWERQWERQWE86 58302b4591 [Doc] Fix group numbering in Case 3 of hybrid_kv_cache_manager.md (#52160) ...

Signed-off-by: qwerqwerqwe8688-jpg <xuuuuu2021@163.com>

2026-08-19 11:38:34 +00:00

..

arch_overview.md

[Frontend] Move api_server.py out openai folder (#52131)

2026-08-19 09:43:46 +00:00

attention_backends.md

[Attention] Integrate FlashAttention 4 SM100 headdim 256 support (#42669)

2026-07-27 18:25:50 +00:00

cuda_graphs_multimodal.md

[ROCm][CI] Enable ViT CUDA graph tests on AMD gfx950 GPUs (#52256)

2026-08-17 09:52:02 +08:00

cuda_graphs.md

…

custom_op.md

[Model] Remove Plamo2 (#49729)

2026-07-24 13:54:24 -07:00

dbo.md

…

debug_vllm_compile.md

…

endpoint_plugins.md

[Frontend] Move api_server.py out openai folder (#52131)

2026-08-19 09:43:46 +00:00

fused_moe_modular_kernel.md

[Bugfix][Doc] Fix references to FusedMoE in doc (#50701)

2026-08-02 09:13:06 +08:00

fusions.md

[Misc][Docs] Fix broken csrc kernel links in fusions doc (#47211)

2026-07-20 09:44:25 +00:00

huggingface_integration.md

…

hybrid_kv_cache_manager.md

[Doc] Fix group numbering in Case 3 of hybrid_kv_cache_manager.md (#52160)

2026-08-19 11:38:34 +00:00

io_processor_plugins.md

…

logits_processors.md

…

lora_resolver_plugins.md

…

metrics.md

[Misc] Remove deprecated calculate_kv_scales runtime KV scale calculation (#49389)

2026-08-03 11:15:13 -04:00

mm_processing.md

replace batch_norm to numerically identical without cudnn (#51734)

2026-08-11 12:43:20 +08:00

model_runner_v2.md

[MRV2][Spec] Fuse AR speculator multi-step decodes back into one CUDA graph (#46849)

2026-08-11 15:06:22 +08:00

moe_kernel_features.md

[MoE] Refine FlashInfer one-sided All2All integration (#51924)

2026-08-18 00:18:14 +00:00

multiprocessing.md

…

nixl_kv_cache_lease.md

[NIXL] Avoid reading expired blocks in bidirectional turn-2 read (#47021)

2026-07-14 13:03:41 +00:00

nixl_kv_push_connector.md

[PD][NixlPush][Bugfix] Fix blocking handshake call on writer thread (#49221)

2026-07-24 01:41:37 -07:00

optimization_levels.md

…

paged_attention.md

…

plugin_system.md

…

prefix_caching.md

…

torch_compile_multimodal.md

…

torch_compile.md

…

vllm_ir.md

…