-
Notifications
You must be signed in to change notification settings - Fork 20k
Issues
is:issue state:open
is:issue state:open
Issue creation is restricted in this repository
Search results
Feature Request: DSpark confidence-scheduled verification & semi-autoregressive drafting
enhancementNew feature or requestNew feature or requestStatus: Open.#25096 In ggml-org/llama.cpp;- Status: Open.#25095 In ggml-org/llama.cpp;
- Status: Open.#25094 In ggml-org/llama.cpp;
- Status: Open.#25088 In ggml-org/llama.cpp;
Feature Request: Add a docker target for the llama app
enhancementNew feature or requestNew feature or requestStatus: Open.#25083 In ggml-org/llama.cpp;HIP/ROCm: system RAM grows unbounded with parallel slots due to CUDA graph cache never being evicted
Status: Open.#25082 In ggml-org/llama.cpp;- Status: Open.#25072 In ggml-org/llama.cpp;
- Status: Open.#25067 In ggml-org/llama.cpp;
Feature Request: Router mode - Do not reload model files if they are already loaded.
enhancementNew feature or requestNew feature or requestStatus: Open.#25066 In ggml-org/llama.cpp;- Status: Open.#25062 In ggml-org/llama.cpp;
- Status: Open.#25061 In ggml-org/llama.cpp;
- Status: Open.#25060 In ggml-org/llama.cpp;