b8zhong f374623fa9 [Refactor] Set fp4-gemm-backend=auto on SM100 and rename fp4-gemm-backend with flashinfer_ prefix (#17309)

2026-01-19 20:09:07 +08:00

..

attention_backend.md

…

checkpoint_engine.md

…

cuda_graph_for_multi_modal_encoder.md

…

deterministic_inference.md

…

dp_for_multi_modal_encoder.md

…

epd_disaggregation.md

…

expert_parallelism.md

[Docs] minor update on ep docs (#17242)

2026-01-16 18:20:47 -08:00

forward_hooks.md

…

hicache_best_practices.md

…

hicache_design.md

…

hicache.rst

…

hyperparameter_tuning.md

…

lora.ipynb

[Feature] overlap LoRA weight loading with compute (#15512)

2026-01-19 10:43:17 +08:00

observability.md

…

pd_disaggregation.md

[NPU] upgrade npu mf_apater plugin (#15853)

2026-01-13 09:02:10 +08:00

pipeline_parallelism.md

…

quantization.md

[AMD][Quantization] Add int4fp8_moe online quantization on ROCm (#7392)

2026-01-14 01:44:40 -08:00

quantized_kv_cache.md

…

rfork.md

support non disturbing remote instance weight loader v2 (#14997)

2025-12-16 14:39:56 -08:00

separate_reasoning.ipynb

docs only add kimi k2 thinking and kimi linear (#15789)

2026-01-15 12:09:52 -05:00

server_arguments.md

[Refactor] Set fp4-gemm-backend=auto on SM100 and rename fp4-gemm-backend with flashinfer_ prefix (#17309)

2026-01-19 20:09:07 +08:00

sgl_model_gateway.md

[model-gateway] Add Redis support as a history backend (#16300)

2026-01-11 01:03:00 -08:00

speculative_decoding.ipynb

…

structured_outputs_for_reasoning_models.ipynb

…

structured_outputs.ipynb

…

tool_parser.ipynb

…

vlm_query.ipynb

…