dynamo/lib/bindings/python/rust/llm
Yan Ru Pei ae4e96a2bc
fix: mocker engines should ignore downloading weights from hf (again) (#3664)
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2025-10-16 02:48:40 +00:00
..
block_manager fix: avoid offload redundant prefill blocks | fix cuda graph hanging (#3632) 2025-10-15 10:38:35 -07:00
backend.rs fix: Load the tokenizer JSON once for chat and completions. (#2910) 2025-09-05 16:48:16 -04:00
block_manager.rs feat: rm the old KVBM metrics | update G2 to G3 metrics collection (#3561) 2025-10-11 01:48:09 +00:00
disagg_router.rs chore: Remove more extended Apache headers (#3063) 2025-09-16 15:48:51 -04:00
entrypoint.rs fix: mocker engines should ignore downloading weights from hf (again) (#3664) 2025-10-16 02:48:40 +00:00
kv.rs feat: dp rank routing (#3597) 2025-10-16 01:48:27 +00:00
local_model.rs feat: dp rank routing (#3597) 2025-10-16 01:48:27 +00:00
model_card.rs feat: Make part of discovery re-usable (#3073) 2025-09-17 10:43:24 -04:00
preprocessor.rs chore: Upgrade Rust to 1.90 (#3147) 2025-09-19 18:54:29 -04:00