jc d5518463ce Mooncake storage register local buffer by chunk (#7416) (#7540)

2026-04-22 10:46:57 +08:00

..

images

…

chunked_prefill.md

…

data_parallel_service.md

…

disaggregated.md

[Docs] Add docs for disaggregated deployment (#6700)

2026-04-01 19:27:09 +08:00

early_stop.md

…

global_cache_pooling.md

Mooncake storage register local buffer by chunk (#7416) (#7540)

2026-04-22 10:46:57 +08:00

graph_optimization.md

…

load_balance.md

…

logits_processor.md

…

multi-node_deployment.md

…

paddleformers_backend.md

…

plas_attention.md

…

plugins.md

…

pooling_models.md

…

prefix_caching.md

…

reasoning_output.md

…

sampling.md

[Feature][Sampling] Extend top-k_top-p sampling to all backends and unify greedy decoding with top_k=1 (#6894)

2026-03-19 01:43:10 -07:00

speculative_decoding.md

[Speculative Decoding] Unify Spec and non-spec branch (#6685)

2026-03-10 23:58:44 -07:00

structured_outputs.md

…

thinking_budget.md

[Bugfix] Align thinking_budget behavior with ERNIE reasoning flow (#6934)

2026-03-23 14:15:55 +08:00

tool_calling.md

…

weight_update.md

[RL] Adapt async rollout checkpoint update flow (#7042)

2026-03-30 19:19:34 +08:00