v0.3.16-cu126-Basic-win-20251112

feat: Update LlamaContext API and Release the model pointer when the ctx was failed to create context with model
feat: Refining the AVX instruction compilation workflow
feat: Use httplib to download model from an URL when the libcurl is disabled
feat: Update Submodule vendor/llama.cpp 7d019cf..017ecee
patch: Fixed CMake Error at vendor/llama.cpp/tools/mtmd/CMakeLists.txt:16 (set_target_properties)

v0.3.16-cu124-Basic-win-20251112

feat: Update LlamaContext API and Release the model pointer when the ctx was failed to create context with model
feat: Refining the AVX instruction compilation workflow
feat: Use httplib to download model from an URL when the libcurl is disabled
feat: Update Submodule vendor/llama.cpp 7d019cf..017ecee
patch: Fixed CMake Error at vendor/llama.cpp/tools/mtmd/CMakeLists.txt:16 (set_target_properties)

v0.3.16-cu126-Basic-win-20251109

feat: Update Submodule vendor/llama.cpp 48bd265..299f5d7
feat: Update llama.cpp API and supplementing the State/sessions API
feat: Better Qwen3VL chat template. (Thank to @alcoftTAO)

Note: llama_chat_template now allows for more flexible input of parameters required by the model and the application of more complex Jinja formats.
The initial input parameters for Qwen3VLChatHandler have changed: "use_think_prompt" has been changed to "force_reasoning".

v0.3.16-cu124-Basic-win-20251109

feat: Update Submodule vendor/llama.cpp 48bd265..299f5d7
feat: Update llama.cpp API and supplementing the State/sessions API
feat: Better Qwen3VL chat template. (Thank to @alcoftTAO)

Note: llama_chat_template now allows for more flexible input of parameters required by the model and the application of more complex Jinja formats.
The initial input parameters for Qwen3VLChatHandler have changed: "use_think_prompt" has been changed to "force_reasoning".

v0.3.16-cu128-AVX2-win-20251108

feat: Update Submodule vendor/llama.cpp 48bd265..299f5d7
feat: Update llama.cpp API and supplementing the State/sessions API
feat: Better Qwen3VL chat template. (Thank to @alcoftTAO)

Note: llama_chat_template now allows for more flexible input of parameters required by the model and the application of more complex Jinja formats.
The initial input parameters for Qwen3VLChatHandler have changed: "use_think_prompt" has been changed to "force_reasoning".