-
Notifications
You must be signed in to change notification settings - Fork 20.4k
Issues
is:issue state:open
is:issue state:open
Issue creation is restricted in this repository
Search results
- Status: Open.#25511 In ggml-org/llama.cpp;
- Status: Open.#25510 In ggml-org/llama.cpp;
Misc. bug: llama.cpp web UI makes requests to third-party services before a user has opted into them
Status: Open.#25509 In ggml-org/llama.cpp;- Status: Open.#25496 In ggml-org/llama.cpp;
Vulkan: remove redundant per-Q-workgroup KV dequant in coopmat1 flash attention
enhancementNew feature or requestNew feature or requestStatus: Open.#25491 In ggml-org/llama.cpp;MTP feature performance drops since b9935
bugSomething isn't workingSomething isn't workingregressionA regression introduced in a new build (something that was previously working correctly)A regression introduced in a new build (something that was previously working correctly)speculativeBugs related to the speculative decoding mechanisms, including MTP, ngram, EAGLE and DflashBugs related to the speculative decoding mechanisms, including MTP, ngram, EAGLE and DflashStatus: Open.- Status: Open.#25488 In ggml-org/llama.cpp;
- Status: Open.#25487 In ggml-org/llama.cpp;
- Status: Open.#25477 In ggml-org/llama.cpp;
- Status: Open.#25468 In ggml-org/llama.cpp;
- Status: Open.#25461 In ggml-org/llama.cpp;