Woosuk Kwon f4359a70f9 [DSV4][Minor] Fix supported KV cache dtypes (#44892) ...

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>

2026-06-16 00:14:51 +00:00

..

arch_overview.md

[Docs] Reorganize online serving docs. (#41907)

2026-05-19 14:43:18 +08:00

attention_backends.md

[DSV4][Minor] Fix supported KV cache dtypes (#44892)

2026-06-16 00:14:51 +00:00

cuda_graphs_multimodal.md

[MM][Perf][CG] Support ViT full cudagraphs for mllama4 (#40660)

2026-06-11 22:17:55 -07:00

cuda_graphs.md

[torch.compile] Refactor Attention Quant Fusion Pass and Remove Boilerplate (#37373)

2026-03-31 14:15:50 -04:00

custom_op.md

[MoE] Move various experts classes to fused_moe/experts/ (#41979)

2026-05-11 07:54:33 +08:00

dbo.md

…

debug_vllm_compile.md

[vLLM IR] 2/N fused_add_rms_norm and maybe_inplace overload (#36823)

2026-05-01 23:41:15 -04:00

fused_moe_modular_kernel.md

…

fusions.md

[Kernel] Porting fuse_minimax_qk_norm to manual fusion (#43410)

2026-05-26 13:16:03 -07:00

huggingface_integration.md

[Frontend] Rework fastokens integration (#43168)

2026-05-21 15:36:58 -07:00

hybrid_kv_cache_manager.md

…

io_processor_plugins.md

…

logits_processors.md

…

lora_resolver_plugins.md

[Docs] Update server entrypoint examples (#42077)

2026-05-09 02:03:52 +00:00

metrics.md

[Examples] Resettle Observability examples. (#40123)

2026-04-17 03:13:31 -07:00

mm_processing.md

…

model_runner_v2.md

…

moe_kernel_features.md

Deprecations for v0.23 and v0.24 (#44992)

2026-06-11 14:35:38 +00:00

multiprocessing.md

…

nixl_kv_cache_lease.md

[NixlConnector] Initiate deprecation cycle for kv_both role (#43874)

2026-06-05 11:08:17 +02:00

nixl_kv_push_connector.md

[KV Connector]: Support KV push from Prefill to Decode node using Nixl KV Connector (#35264)

2026-06-12 10:38:41 +00:00

optimization_levels.md

[Docs] Update server entrypoint examples (#42077)

2026-05-09 02:03:52 +00:00

paged_attention.md

…

plugin_system.md

…

prefix_caching.md

…

torch_compile_multimodal.md

[Doc] Fix multimodal torch.compile troubleshooting to not use removed VLLM_TORCH_COMPILE_LEVEL (#44378)

2026-06-07 00:34:07 -07:00

torch_compile.md

…

vllm_ir.md

[vLLM IR] 2/N fused_add_rms_norm and maybe_inplace overload (#36823)

2026-05-01 23:41:15 -04:00