Benjamin Chislett 304419576a

[Perf] Refactor cudagraph_support to enable full CUDA graphs for spec decoding with FlashInfer (#28479) ...

Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>

2025-11-13 01:56:40 +09:00

..

arch_overview.md

…

cuda_graphs.md

[Perf] Refactor cudagraph_support to enable full CUDA graphs for spec decoding with FlashInfer (#28479)

2025-11-13 01:56:40 +09:00

dbo.md

…

debug_vllm_compile.md

[Docs] Add guide to debugging vLLM-torch.compile integration (#28094)

2025-11-05 21:31:46 +00:00

fused_moe_modular_kernel.md

…

huggingface_integration.md

…

hybrid_kv_cache_manager.md

…

io_processor_plugins.md

[Frontend][Doc][5/N] Improve all pooling task | Polish encode (pooling) api & Document. (#25524)

2025-10-30 12:13:05 +00:00

logits_processors.md

[Bugfix] Validate custom logits processor xargs for online serving (#27560)

2025-11-05 16:53:33 +00:00

metrics.md

[Doc] Fix minor issues in docs/design/metrics.md (#27436)

2025-10-24 05:40:54 -07:00

mm_processing.md

…

moe_kernel_features.md

[RFC][ROCm][AITER] Keep all AITER kernels in _aiter_ops class like _custom_ops and _ipex_ops (#24490)

2025-11-10 08:20:53 -08:00

multiprocessing.md

…

p2p_nccl_connector.md

…

paged_attention.md

…

plugin_system.md

…

prefix_caching.md

[Doc] Fix numbering sequence in prefix caching (#27357)

2025-10-22 17:35:47 +00:00

torch_compile.md

[BUG] Make 'binary' default option for saving torch compile artifacts when using standalone_compile (#27616)

2025-11-03 11:13:51 -05:00