forked from ggml-org/llama.cpp
- Notifications
You must be signed in to change notification settings - Fork 15
All issues
Issue creation is restricted in this repository
Issues
is:issuestate:open
is:issue state:open
Search results
server: concurrent router loads can leave one model queued forever
bugSomething isn't workingSomething isn't workingStatus: Open.#36In am17an/llama.cpp;server: streaming tools reject logprobs while n_probs works
bugSomething isn't workingSomething isn't workingStatus: Open.#35In am17an/llama.cpp;server: id_slot pinned to an empty slot skips the prompt cache
bugSomething isn't workingSomething isn't workingStatus: Open.#34In am17an/llama.cpp;server: tool_choice required does not require a tool call
bugSomething isn't workingSomething isn't workingStatus: Open.#33In am17an/llama.cpp;server: Gemma 4 typed-content template is classified unsupported
bugSomething isn't workingSomething isn't workingStatus: Open.#31In am17an/llama.cpp;server: Unicode tool properties collide in PEG grammar
bugSomething isn't workingSomething isn't workingStatus: Open.#30In am17an/llama.cpp;CUDA: q5_1 KV with FlashAttention silently runs on CPU
bugSomething isn't workingSomething isn't workingStatus: Open.#28In am17an/llama.cpp;