Commits
User selector
Commit history
Commits on Mar 4, 2026
Fix locale-dependent float printing in GGUF metadata (#17331)
Show description for cb8f4faandauthored
Commits on Sep 17, 2025
examples : support encoder-decoder models in the simple example (#16002)
Show description for 1cbd80fauthored
Commits on May 19, 2025
Commits on Jan 12, 2025
llama : add `llama_vocab`, functions -> methods, naming (#11110)
Show description for afa8a9eandauthored
Commits on Jan 6, 2025
llama : update llama_model API names (#11063)
Show description for 47182ddauthored
Commits on Nov 29, 2024
ggml : move AMX to the CPU backend (#10570)
Show description for 7cc2d2candauthored
Commits on Nov 28, 2024
Commits on Nov 25, 2024
ggml : add support for dynamic loading of backends (#10469)
Show description for 5931c1fandauthored
Commits on Oct 18, 2024
llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)
Show description for cda0e4bauthored
Commits on Oct 10, 2024
examples : do not use common library in simple example (#9803)
Show description for c7499c5authored
Commits on Sep 15, 2024
common : reimplement logging (#9418)
Show description for 6262d13authored
Commits on Sep 13, 2024
llama : llama_perf + option to disable timings during decode (#9355)
Show description for 0abc6a2andauthored
Commits on Sep 9, 2024
common : move arg parser code to `arg.cpp` (#9388)
Show description for bfe76d4andauthored- authored
Commits on Sep 7, 2024
common : refactor arg parser (#9308)
Show description for 1b9ae51authoredllama : refactor sampling v2 (#9294)
Show description for df270efauthored
Commits on Aug 6, 2024
simple : update name of executable to llama-simple (#8885)
Show description for 5f4dcb1authored
Commits on Jun 12, 2024
`build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)
Show description for 1c641e6andauthored
Commits on Jun 4, 2024
common : refactor cli arg parsing (#7675)
Show description for 1442677authored
Commits on Apr 21, 2024
llama : support Llama 3 HF conversion (#6745)
Show description for b97bc39authored
Commits on Feb 16, 2024
ggml : add numa options (#5377)
Show description for f486f6eauthored
Commits on Dec 4, 2023
simple : update error message for KV cache check (#4324)
Show description for 23b5e12authored
Commits on Oct 27, 2023
Commits on Oct 23, 2023
llama : remove token functions with `context` args in favor of `model` (#3720)
Show description for 5be6c80andauthored
Commits on Oct 18, 2023
speculative : add tree-based sampling example (#3624)
Show description for 0e89203authored
Commits on Sep 28, 2023
llama.cpp : split llama_context_params into model and context params (#3301)
Show description for 16bc66dauthoredllama : custom attention mask + parallel decoding + no context swaps (#3228)
Show description for ec89379andauthored
Commits on Sep 15, 2023
Commits on Sep 8, 2023
build : do not use _GNU_SOURCE gratuitously (#2035)
Show description for cb6c44cauthored
Commits on Aug 27, 2023
llama : more tokenizer fixes (#2810)
Show description for edd4c14andauthored
Commits on Aug 21, 2023
gguf : new file format with flexible meta data (beta) (#2398)
Show description for 6381d4eauthored
Commits on Aug 4, 2023
Commits on Jul 19, 2023
cmake : install targets (#2256)
Show description for b1f4290authored
Commits on Jul 10, 2023
mpi : add support for distributed inference via MPI (#2099)
Show description for 5656d10andauthored
Commits on Jun 26, 2023
ggml : add NUMA support (#1556)
Show description for b853d45andauthored