Commit History

Auteur SHA1 Bericht Datum
  Jeff Bolz 303f8615e9 vulkan: Multi-pass softmax for large number of cols (#17892) 1 maand geleden
  Georgi Gerganov 3c6391e748 speculative-simple : free batch on exit (#17985) 1 maand geleden
  Sigbjørn Skjæret 8e4d678528 common : skip model validation when --completion-bash is requested (#17975) 1 maand geleden
  Jeff Bolz 07a10c1090 vulkan: Allow non-pow2 n_experts in topk_moe (#17872) 1 maand geleden
  Sigbjørn Skjæret 2bc94e7928 add llama-completion to completion-bash executables (#17976) 1 maand geleden
  Daniel Bevenius fd1085ffb7 model-conversion : use CONVERTED_MODEL value for converted model [no ci] (#17984) 1 maand geleden
  Xuan-Son Nguyen 380b4c984e common: support negated args (#17919) 1 maand geleden
  Xuan-Son Nguyen e39a2ce66d clip: move model cgraphs into their own files (#17965) 1 maand geleden
  jiahao su a8c7f33d79 ci : change the cann version and the container pull method (#17953) 1 maand geleden
  Sigbjørn Skjæret b7f5f46e03 docker : include legacy llama-completion binary (#17964) 1 maand geleden
  Johannes Gäßler 482211438d CUDA: fix overflow in MMA kernel without stream-k (#17939) 1 maand geleden
  Georgi Gerganov 7bed317f53 models : fix the attn_factor for mistral3 graphs + improve consistency (#17945) 1 maand geleden
  Sigbjørn Skjæret dcb7d17758 cann : fix ops broken by circular padding guard (#17825) 1 maand geleden
  ixgbe 51604435e8 ggml-cpu : fix RISC-V Q4_0 repack select and RVV feature reporting (#17951) 1 maand geleden
  Xuan-Son Nguyen 17158965ac mtmd: explicitly forbidden inclusion of private header and libcommon (#17946) 1 maand geleden
  Aleksander Grygier 12280ae905 webui: Fix parsing non-LaTeX occurrencies of `\(` or `\)` (#17810) 1 maand geleden
  Xuan-Son Nguyen 54a0fee4b7 arg: add -mm and -mmu as short form of --mmproj and --mmproj-url (#17958) 1 maand geleden
  Daniel Bevenius dada4c846d model-conversion : remove max diff check in compare-logits [no ci] (#17954) 1 maand geleden
  Adrien Gallouët b8ee22cfde common : add minimalist multi-thread progress bar (#17602) 1 maand geleden
  Gustavo Rocha Dias 2eaa2c65cb cmake: link ws2_32 for MinGW/w64devkit builds in cpp-httplib (#17949) 1 maand geleden
  yulo c33a58bced HIP: enable mmf for RDNA3 (#17879) 1 maand geleden
  Pascal a81a569577 Add a search field on model selector / improve mobile display (#17765) 1 maand geleden
  Piotr Wilkin (ilintar) 53ecd4fdb9 SOLVE_TRI extension to more dimensions (#17793) 1 maand geleden
  Georgi Gerganov c6f6e4f96a ggml-alloc : fix reuse-parent logic for misaligned sizes (#17884) 1 maand geleden
  Georgi Gerganov d9f8f60618 batch : fix sequence id ownership (#17915) 1 maand geleden
  Yuichiro Utsumi e4ae383317 docs: use port 8080 in Docker examples (#17903) 1 maand geleden
  nullname 34ce48d97a ggml-hexagon: fix `rope` failure at `test-backend-ops` (#17565) 1 maand geleden
  Sigbjørn Skjæret 45e350e3d3 ci: fix riscv64-native build (#17916) 1 maand geleden
  Xuan-Son Nguyen c6b2c9310c mtmd: some small clean up (#17909) 1 maand geleden
  Xuan-Son Nguyen 34a6d86982 cli: enable jinja by default (#17911) 1 maand geleden