Commit History

Автор SHA1 Съобщение Дата
  Jaemin Son e689fc4e91 [bug fix] convert github repository_owner to lowercase (#6673) преди 1 година
  James A Capozzoli a4ec34e1cd convert : enable the `--use-temp-file` cli flag (#6645) преди 1 година
  Neo Zhang Jianyu de17e3f745 fix memcpy() crash, add missed cmd in guide, fix softmax (#6622) преди 1 година
  Johannes Gäßler b5e7285baf CUDA: fix matrix multiplication logic for tests (#6667) преди 1 година
  Pierrick Hymbert 4bd0f93e4a model: support arch `DbrxForCausalLM` (#6515) преди 1 година
  Olivier Chafik ab9a3240a9 JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555) преди 1 година
  slaren fbbc030ba9 metal : unify mul_mv_id kernels (#6556) преди 1 година
  Daniel Bevenius 4cc120c744 infill : add download instructions for model (#6626) преди 1 година
  Pierrick Hymbert 24ee66ed0d server : coherent log output for KV cache full (#6637) преди 1 година
  jiez 91c736015b llama : add gguf_remove_key + remove split meta during quantize (#6591) преди 1 година
  Rene Leonhardt 5c4d767ac0 chore: Fix markdown warnings (#6625) преди 1 година
  Georgi Gerganov ef21ce4ccb imatrix : remove invalid assert (#6632) преди 1 година
  MasterYi1024 dee7f8d692 Correct free memory and total memory. (#6630) преди 1 година
  Pierrick Hymbert 81da18e71c eval-callback: use ggml_op_desc to pretty print unary operator name (#6631) преди 1 година
  Georgi Gerganov 9ed2737acc ci : disable Metal for macOS-latest-cmake-x64 (#6628) преди 1 година
  Clint Herron 04a5ac211e Optimization: eliminate addition of redundant stacks when advancing grammar. (#6616) преди 1 година
  Clint Herron f7001ccc5a As suggested by @slaren, disabling Metal for test to fix CI build on OSX from #6576 (#6619) преди 1 година
  Nikolas a474f50ebb Refactor Error Handling for CUDA (#6575) преди 1 година
  Olivier Chafik cbaadc9294 grammars: 1.5x faster inference w/ complex grammars (vector reserves / reuses) (#6609) преди 1 година
  Hugo Roussel 1bbdaf6ecd ci: download artifacts to release directory (#6612) преди 1 година
  Daniel Bevenius f4183afe6a scripts : add --outdir option to hf.sh (#6600) преди 1 година
  Pierrick Hymbert b804b1ef77 eval-callback: Example how to use eval callback for debugging (#6576) преди 1 година
  Daniel Bevenius 8228b66dbc gguf : add option to not check tensor data (#6582) преди 1 година
  Ralph Soika b3a96f27f0 minor layout improvements (#6572) преди 1 година
  slaren 4f407a0a35 llama : add model types for mixtral (#6589) преди 1 година
  slaren 65c64dc36f convert.py : add consolidated.safetensors for mixtral 8x22b (#6587) преди 1 година
  Pierrick Hymbert 67fac4b95f docs : how to add a model (#6565) преди 1 година
  Artem Zinnatullin 29122d32ac readme : fix ROCm link (#6579) преди 1 година
  sjxx b231b37b09 readme : update UI list (#6560) преди 1 година
  Jiří Sejkora ba5e134e07 readme: fix typo in amdgpu target name (#6573) преди 1 година