Commit History

Author SHA1 Message Date
  Georgi Gerganov fd1234cb46 llama : add gpt-oss (#15091) 6 months ago
  Oliver Simons e2b7621e7c ggml : remove invalid portPos specifiers from dot files (#14838) 6 months ago
  Xuan-Son Nguyen 98bab638fb ggml : add ggml_scale_bias (#14417) 7 months ago
  Sigbjørn Skjæret 28657a8229 ggml : implement GEGLU_ERF and GEGLU_QUICK ops (#14445) 7 months ago
  Johannes Gäßler c8c4495b8d ggml: backward pass for split swiglu (#14483) 7 months ago
  Georgi Gerganov 9067487c44 ggml : fix FA mask dim 2 and 3 (#14505) 7 months ago
  compilade 5d46babdc2 llama : initial Mamba-2 support (#9126) 7 months ago
  Daniel Bevenius c46944aa25 ggml : add version function to get lib version (ggml/1286) 7 months ago
  Georgi Gerganov ec68e84c32 ggml : support bcast ggml_soft_max_ext, ggml_flash_attn_ext (#14435) 7 months ago
  Björn Ganster 68b3cd6514 ggml : Callback before abort (#14481) 7 months ago
  Georgi Gerganov a6a47958a1 ggml : remove trailing whitespace (#0) 7 months ago
  Acly 431b2c24f3 ggml-cpu : "align corners" for bilinear upscale/downscale (ggml/1285) 7 months ago
  Aman Gupta 0a5a3b5cdf Add Conv2d for CPU (#14388) 7 months ago
  Sigbjørn Skjæret a0535ffa0d ggml : implement REGLU/GEGLU/SWIGLU ops (#14158) 7 months ago
  Jeff Bolz bd9c981d72 vulkan: Add fusion support for RMS_NORM+MUL (#14366) 7 months ago
  Radoslav Gerganov 8d94219a4a ggml : add ggml_set_rows (#14274) 7 months ago
  Aaron Teo 60ef23d6c1 ggml-cpu: enable IBM NNPA Vector Intrinsics (#14317) 7 months ago
  Acly b7147673f2 Add `ggml_roll` (ggml/1274) 7 months ago
  Daniel Bevenius bbe98d2784 ggml : remove unused ggml_context_container (ggml/1272) 8 months ago
  Georgi Gerganov a7b8d35f78 sync : whisper.cpp (ggml/1250) 8 months ago
  Daniel Tang fedf034a98 ggml : Print backtrace on uncaught C++ exceptions (ggml/1232) 8 months ago
  Xuan-Son Nguyen a8ea03d8ad ggml : add ggml_repeat_4d (#13824) 8 months ago
  Xuan-Son Nguyen cf4cb59e64 ggml : add ggml_gelu_erf() (#13667) 8 months ago
  Diego Devesa 8b5e19aea6 ggml : fix apple OS check in ggml_print_backtrace (ggml/1229) 8 months ago
  Daniel Tang 60aea028b5 ggml : Fix missing backtrace on Linux (ggml/1228) 8 months ago
  Johannes Gäßler 10d2af0eaa llama/ggml: add LLM training support (#10544) 9 months ago
  Georgi Gerganov 611aa914ef metal : optimize MoE for large batches (#13388) 9 months ago
  Johannes Gäßler 2356fb1d53 CUDA: fix bad asserts for partial offload (#13337) 9 months ago
  SXX 77d5e9a76a ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs (#13107) 9 months ago
  Georgi Gerganov 87616f0680 ggml : fix trailing whitespaces (#0) 9 months ago