Commits

Commit history

1. Commits on Nov 23, 2023

   • Fix incorrect format strings and uninitialized variables. (#4133)

     Show description for 55978ce
     haohui

     authored
     55978ceView commit details

     Copy full SHA for 55978ce

     Browse repository at this point

   • llama : KV cache view API + better KV cache management (#4170)

     Show description for 6b0a742
     

     ggerganov

     and

     KerfuffleV2

     authored
     6b0a742View commit details

     Copy full SHA for 6b0a742

     Browse repository at this point

   • readme : update hot topics

     ggerganov

     authored
     d103d93View commit details

     Copy full SHA for d103d93

     Browse repository at this point

   • examples : fix typo in parallel example doc comment (#4181)

     Show description for 9d5949f
     danbev

     authored
     9d5949fView commit details

     Copy full SHA for 9d5949f

     Browse repository at this point

   • docs : add llama-star arch idea

     ggerganov

     committed
     ff8238fView commit details

     Copy full SHA for ff8238f

     Browse repository at this point
2. Commits on Nov 21, 2023

   • stablelm : simplify + speedup generation (#4153)

     Galunid

     authored
     8e672efView commit details

     Copy full SHA for 8e672ef

     Browse repository at this point
3. Commits on Nov 20, 2023

   • finetune - update readme to mention llama support only (#4148)

     Galunid

     authored
     0b871f1View commit details

     Copy full SHA for 0b871f1

     Browse repository at this point

   • readme : update ROCm Windows instructions (#4122)

     Show description for dfc7cd4
     

     jammm

     and

     cebtenzzre

     authored
     dfc7cd4View commit details

     Copy full SHA for dfc7cd4

     Browse repository at this point

   • main : Add ChatML functionality to main example (#4046)

     Show description for 881800d
     Sebby37

     authored
     881800dView commit details

     Copy full SHA for 881800d

     Browse repository at this point

   • ci : add flake8 to github actions (python linting) (#4129)

     Show description for f23c035
     Galunid

     authored
     f23c035View commit details

     Copy full SHA for f23c035

     Browse repository at this point

   • speculative : fix prompt tokenization in speculative example (#4025)

     Show description for 40a34fe
     AutonomicPerfectionist

     authored
     40a34feView commit details

     Copy full SHA for 40a34fe

     Browse repository at this point
4. Commits on Nov 19, 2023

   • Revert "finetune : add --n-gpu-layers flag info to --help (#4128)"

     Show description for dae06c0
     ggerganov

     committed
     dae06c0View commit details

     Copy full SHA for dae06c0

     Browse repository at this point

   • finetune : add --n-gpu-layers flag info to --help (#4128)

     csaben

     authored
     05e8301View commit details

     Copy full SHA for 05e8301

     Browse repository at this point

   • server : relay error messages (#4131)

     SoftwareRenderer

     authored
     936c79bView commit details

     Copy full SHA for 936c79b

     Browse repository at this point

   • common : comma should be semicolon (#4137)

     kchro3

     authored
     262005aView commit details

     Copy full SHA for 262005a

     Browse repository at this point

   • gitignore : tokenize

     ggerganov

     committed
     35985acView commit details

     Copy full SHA for 35985ac

     Browse repository at this point

   • gguf-py : export chat templates (#4125)

     Show description for e937066
     slaren

     authored
     e937066View commit details

     Copy full SHA for e937066

     Browse repository at this point
5. Commits on Nov 18, 2023

   • tokenize example: Respect normal add BOS token behavior (#4126)

     Show description for 28a2e6e
     KerfuffleV2

     authored
     28a2e6eView commit details

     Copy full SHA for 28a2e6e

     Browse repository at this point

   • scripts : Remove missed baichuan convert script (#4127)

     Galunid

     authored
     0b5c3b0View commit details

     Copy full SHA for 0b5c3b0

     Browse repository at this point

   • Clean up ggml-cuda.cu warnings when compiling with clang (for ROCM) (#4124)

     Show description for 2923f17
     KerfuffleV2

     authored
     2923f17View commit details

     Copy full SHA for 2923f17

     Browse repository at this point
6. Commits on Nov 17, 2023

   • llama : increase max nodes (#4115)

     slaren

     authored
     bbecf3fView commit details

     Copy full SHA for bbecf3f

     Browse repository at this point

   • build : support ppc64le build for make and CMake (#3963)

     Show description for 8e93610
     

     bufferoverflow

     and

     ggerganov

     authored
     8e93610View commit details

     Copy full SHA for 8e93610

     Browse repository at this point

   • tokenize : fix trailing whitespace

     ggerganov

     committed
     5ad387eView commit details

     Copy full SHA for 5ad387e

     Browse repository at this point

   • examples : add tokenize (#4039)

     zakkor

     authored
     2fa02b4View commit details

     Copy full SHA for 2fa02b4

     Browse repository at this point

   • convert : use 'model' value if it exists. This allows karpathy/tinyllamas to load (#4089)

     Show description for 2ab0707
     dmahurin

     authored
     2ab0707View commit details

     Copy full SHA for 2ab0707

     Browse repository at this point

   • py : Falcon HF compatibility (#4104)

     Show description for 11173c9
     cmp-nct

     authored
     11173c9View commit details

     Copy full SHA for 11173c9

     Browse repository at this point

   • common : improve yaml log escaping (#4080)

     Show description for 9e87ef6
     joennlae

     authored
     9e87ef6View commit details

     Copy full SHA for 9e87ef6

     Browse repository at this point

   • llava : fix compilation warning that fread return value is not used (#4069)

     huawei-lin

     authored
     c7cce12View commit details

     Copy full SHA for c7cce12

     Browse repository at this point

   • py : remove superfluous import statements (#4076)

     Show description for f7d5e97
     jpodivin

     authored
     f7d5e97View commit details

     Copy full SHA for f7d5e97

     Browse repository at this point

   • train : move number of gpu layers argument parsing to common/train.cpp (#4074)

     Show description for ba4cf5c
     jpodivin

     authored
     ba4cf5cView commit details

     Copy full SHA for ba4cf5c

     Browse repository at this point

   • llama : add functions to get the model's metadata (#4013)

     Show description for e85bb1a
     slaren

     authored
     e85bb1aView commit details

     Copy full SHA for e85bb1a

     Browse repository at this point

   • finetune : speed-up ggml_compute_forward_out_prod_f32 via BLAS (#4079)

     Show description for 3e916a0
     gwjr

     authored
     3e916a0View commit details

     Copy full SHA for 3e916a0

     Browse repository at this point

   • finetune : zero the loraB initial vectors (#4082)

     Show description for 947f64f
     AndrewGodfrey

     authored
     947f64fView commit details

     Copy full SHA for 947f64f

     Browse repository at this point

   • cuda : get_row_rounding F32 (#4095)

     Show description for b83e149
     

     AndrewGodfrey

     and

     cebtenzzre

     authored
     b83e149View commit details

     Copy full SHA for b83e149

     Browse repository at this point

   • llama : fix data units (#4101)

     Show description for 4f447a4
     ggerganov

     authored
     4f447a4View commit details

     Copy full SHA for 4f447a4

     Browse repository at this point