b8zhong a076ec1a7a Revert "fix llama4 kv cache layout" (#12437)

2025-10-30 22:33:37 -07:00

..

attention_backend.md

Revert "fix llama4 kv cache layout" (#12437)

2025-10-30 22:33:37 -07:00

checkpoint_engine.md

[Ckpt Engine] feat: new sglang entrypoint support for update (#12216)

2025-10-30 10:39:27 +08:00

deterministic_inference.md

…

hicache_best_practices.md

…

hicache_design.md

…

hicache.rst

…

hyperparameter_tuning.md

…

lora.ipynb

…

observability.md

…

pd_disaggregation.md

…

pd_multiplexing.md

…

quantization.md

Add support for AutoRound quantized models (#10153)

2025-10-27 18:17:29 +08:00

router.md

…

separate_reasoning.ipynb

[Doc] Add documentation for DeepSeek V3.2 (#11877)

2025-10-24 19:06:22 -07:00

server_arguments.md

Remove description for --enable-beta-spec argument (#12177)

2025-10-26 16:49:39 -07:00

speculative_decoding.ipynb

…

structured_outputs_for_reasoning_models.ipynb

…

structured_outputs.ipynb

…

tool_parser.ipynb

…

vlm_query.ipynb

…