Commit History

Author SHA1 Message Date
  Georgi Gerganov d48ccf3ad4 sync : ggml (#6351) 1 year ago
  hxer7963 069574775c [Model] Add support for xverse (#6301) 1 year ago
  Georgi Gerganov cfde806eb9 ci : fix BGE wget (#6383) 1 year ago
  zhouwg b910287954 readme : add project (#6356) 1 year ago
  Matt Clayton 8093987090 cmake : add explicit metal version options (#6370) 1 year ago
  Daniel Bevenius 057400a3fd llama : remove redundant reshape in build_kv_store (#6369) 1 year ago
  Pedro Cuenca b75c38166c convert : allow conversion of Mistral HF models (#6144) 1 year ago
  Georgi Gerganov bfe7dafc9c readme : add notice for UI list 1 year ago
  Ouadie EL FAROUKI 5106ef482c [SYCL] Revisited & updated SYCL build documentation (#6141) 1 year ago
  Jared Van Bortel be55134a53 convert : refactor vocab selection logic (#6355) 1 year ago
  Ziang Wu 66ba560256 llava : fix MobileVLM (#6364) 1 year ago
  compilade 0308f5e3d7 llama : fix command-r inference when omitting outputs (#6367) 1 year ago
  Pierrick Hymbert 28cb9a09c4 ci: bench: fix master not schedule, fix commit status failed on external repo (#6365) 1 year ago
  Ting Sun cfc4d75df6 doc: fix outdated default value of batch size (#6336) 1 year ago
  Eric Zhang 6902cb7f2e server : stop gracefully on SIGTERM (#6348) 1 year ago
  hutli d2d8f38996 nix: removed unnessesary indentation 1 year ago
  hutli d39b308eaf nix: moved blas availability check to package inputs so it is still overridable 1 year ago
  hutli c873976649 using blas.meta.available to check host platform 1 year ago
  hutli dbb03e2b9c only using explicit blas if hostPlatform is allowed 1 year ago
  Someone Serge e9f17dc3bf nix: .#windows: proper cross-compilation set-up 1 year ago
  Someone Serge 22a462cc1f nix: package: don't introduce the dependency on python 1 year ago
  hutli f6a0f5c642 nix: .#widnows: init 1 year ago
  Ziang Wu d0e2f6416b doc: fix typo in MobileVLM-README.md (#6181) 1 year ago
  Neo Zhang Jianyu 25f4a613c4 [SYCL] fix set main gpu crash (#6339) 1 year ago
  Pierrick Hymbert a016026a3a server: continuous performance monitoring and PR comment (#6283) 1 year ago
  Someone Serge 53c7ec53d5 nix: ci: dont test cuda and rocm (for now) 1 year ago
  slaren e5b89a441a ggml : fix bounds checking of zero size views (#6347) 1 year ago
  Georgi Gerganov 3a0345970e make : whitespace 1 year ago
  howlger 1e13987fba embedding : show full embedding for single prompt (#6342) 1 year ago
  AidanBeltonS e82f9e2b83 [SYCL] Fix batched impl for NVidia GPU (#6164) 1 year ago