Issues
state:open label:refactoring
state:open label:refactoring
Search results
ggml : refactor ggml-cpu.c into multiple C++ source files
refactoringRefactoringRefactoringroadmapPart of a roadmap projectPart of a roadmap projectStatus: Open.#10180 In ggml-org/llama.cpp;imatrix : use GGUF to store importance matrices
breaking changeChanges that break ABIs, APIs, file formats, or other forms of backwards compatibility.Changes that break ABIs, APIs, file formats, or other forms of backwards compatibility.enhancementNew feature or requestNew feature or requestpythonpython script changespython script changesrefactoringRefactoringRefactoringReview Complexity : MediumGenerally require more time to grok but manageable by beginner to medium expertise levelGenerally require more time to grok but manageable by beginner to medium expertise levelStatus: Draft (not ready).ggml-org/llama.cppnumber 9400#9400 In ggml-org/llama.cpp;Refactor: Add more typechecking to GGUFWriter.add_key_value
help wantedExtra attention is neededExtra attention is neededrefactoringRefactoringRefactoringStatus: Open.#9095 In ggml-org/llama.cpp;Refactor: Existing examples refactoring opportunities
help wantedExtra attention is neededExtra attention is neededrefactoringRefactoringRefactoringStatus: Open.#7559 In ggml-org/llama.cpp;llama : support Jamba hybrid Transformer-Mamba models
androidIssues specific to AndroidIssues specific to Androidembeddingsembedding related topicsembedding related topicsenhancementNew feature or requestNew feature or requestggmlchanges relating to the ggml tensor library for machine learningchanges relating to the ggml tensor library for machine learningmodelModel specificModel specificneed feedbackTesting and feedback with results are neededTesting and feedback with results are neededpythonpython script changespython script changesrefactoringRefactoringRefactoringReview Complexity : HighGenerally require indepth knowledge of LLMs or GPUsGenerally require indepth knowledge of LLMs or GPUsStatus: Draft (not ready).ggml-org/llama.cppnumber 7531#7531 In ggml-org/llama.cpp;common, ngram_cache: added const reference for std::pair<> and std::tuple<> more 16 bytes:
refactoringRefactoringRefactoringReview Complexity : LowTrivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fixTrivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fixStatus: Open (in progress).ggml-org/llama.cppnumber 7270#7270 In ggml-org/llama.cpp;ggml, ngram-cache, log: added const and const ref for function params
refactoringRefactoringRefactoringReview Complexity : MediumGenerally require more time to grok but manageable by beginner to medium expertise levelGenerally require more time to grok but manageable by beginner to medium expertise levelStatus: Open (in progress).ggml-org/llama.cppnumber 7269#7269 In ggml-org/llama.cpp;tokenization: no double BOS tokens
refactoringRefactoringRefactoringReview Complexity : MediumGenerally require more time to grok but manageable by beginner to medium expertise levelGenerally require more time to grok but manageable by beginner to medium expertise levelStatus: Open (in progress).ggml-org/llama.cppnumber 7107#7107 In ggml-org/llama.cpp;ggml : unified CMake build
buildCompilation issuesCompilation issuesenhancementNew feature or requestNew feature or requestrefactoringRefactoringRefactoringroadmapPart of a roadmap projectPart of a roadmap projectStatus: Open.#6913 In ggml-org/llama.cpp;Refactor chat template API
demoDemonstrate some concept or idea, not intended to be mergedDemonstrate some concept or idea, not intended to be mergedrefactoringRefactoringRefactoringReview Complexity : MediumGenerally require more time to grok but manageable by beginner to medium expertise levelGenerally require more time to grok but manageable by beginner to medium expertise levelStatus: Draft (not ready).ggml-org/llama.cppnumber 6822#6822 In ggml-org/llama.cpp;llama : switch to floating-point token positions
demoDemonstrate some concept or idea, not intended to be mergedDemonstrate some concept or idea, not intended to be mergedrefactoringRefactoringRefactoringReview Complexity : HighGenerally require indepth knowledge of LLMs or GPUsGenerally require indepth knowledge of LLMs or GPUsStatus: Draft (not ready).ggml-org/llama.cppnumber 5679#5679 In ggml-org/llama.cpp;P-Step Truncation Sampling
generation qualityQuality of model outputQuality of model outputneed feedbackTesting and feedback with results are neededTesting and feedback with results are neededrefactoringRefactoringRefactoringReview Complexity : HighGenerally require indepth knowledge of LLMs or GPUsGenerally require indepth knowledge of LLMs or GPUsStatus: Open (in progress).ggml-org/llama.cppnumber 5675#5675 In ggml-org/llama.cpp;