Ke Bao 3aa11ca722 Remove hybrid_kvcache_ratio in server args (#16399)

2026-01-06 13:13:13 +08:00

..

deepseek_v3.md

…

deepseek_v32.md

Multiple refactors of DeepSeek V32 and context parallel (#16305)

2026-01-03 02:21:22 +08:00

glm45.md

[GLM-4.7] GLM-4.7 Tool Parser and Doc Update (#15333)

2025-12-19 20:30:44 -08:00

glmv.md

…

gpt_oss.md

…

llama4.md

Remove hybrid_kvcache_ratio in server args (#16399)

2026-01-06 13:13:13 +08:00

minimax_m2.md

Update MiniMax-M2 ToolCall and add MiniMax-M2.1 in Docs (#15538)

2025-12-23 15:11:52 -08:00

native_api.ipynb

…

offline_engine_api.ipynb

…

ollama_api.md

Add Ollama-compatible API endpoints + Smart Router (#14376)

2025-12-16 20:43:38 -08:00

openai_api_completions.ipynb

…

openai_api_embeddings.ipynb

…

openai_api_vision.ipynb

…

openai_api.rst

…

popular_model_usage.rst

Update MiniMax-M2 ToolCall and add MiniMax-M2.1 in Docs (#15538)

2025-12-23 15:11:52 -08:00

qwen3_vl.md

…

qwen3.md

Add doc for qwen3 next (#15337)

2025-12-17 17:53:07 -08:00

sampling_params.md

vlm: refactor engine vlm params and support processor output as input (#14091)

2025-12-20 18:31:24 +08:00

send_request.ipynb

…