Cronologia Commit

Autore SHA1 Messaggio Data
  Yavor Ivanov dcf7f2ea3c metal : Add missing unary ops Metal support (#14660) 6 mesi fa
  Yavor Ivanov 84b396e051 cmake : Add CMake presets for Linux and GCC (#14656) 6 mesi fa
  Tarek Dakhran c31e60647d tests : cover lfm2 cases in test_ssm_conv (#14651) 6 mesi fa
  Tarek Dakhran 67eade1bf9 docs : add LFM2 to models section (#14650) 6 mesi fa
  Aman Gupta 7de5c7cab6 CUDA: add set rows for f32 and f16 (#14551) 6 mesi fa
  Georgi Gerganov 8eff95544e sync : ggml 6 mesi fa
  Georgi Gerganov 3120413ccd vulkan : remove unused vars (#0) 6 mesi fa
  Georgi Gerganov 215535701d sync : ggml 6 mesi fa
  Acly 74bb294591 vulkan : implement bilinear interpolation (ggml/1291) 6 mesi fa
  Acly 3e303b1107 vulkan : implement ggml_roll (ggml/1290) 6 mesi fa
  Douglas Hanley 0c1df14b5f server : fix pooled embedding output (#14645) 6 mesi fa
  Jeff Bolz b3ad3a0191 vulkan: support SET_ROWS (#14587) 6 mesi fa
  Jeff Bolz 98197e5c98 vulkan: optimizations for deepseek prompt processing (#14555) 6 mesi fa
  Tarek Dakhran f5e96b368f model : support LiquidAI LFM2 hybrid family (#14620) 6 mesi fa
  Slobodan Josic 756aa1020a HIP : Add HIP 7.0+ compatibility for hipBLAS compute types (#14634) 6 mesi fa
  Georgi Gerganov aaa088d87f readme : add hot PRs (#14636) 6 mesi fa
  Georgi Gerganov 0d5375d54b llama : move enum llama_vocab_pre_type to implementation (#14631) 6 mesi fa
  Dowon 576c82eda2 vocab : add midm-2.0 model pre-tokenizer (#14626) 6 mesi fa
  Gabe Goodhart 0aedae00e6 model : Granite Four (#13550) 6 mesi fa
  rmatif 6bdda13981 opencl: add tiled mul_mat_f16_f32 (#14535) 6 mesi fa
  lhez 0b8855775c opencl: add `set_rows` for `f16` and `f32` (#14547) 6 mesi fa
  Ryan Mangeno 4bb625b713 Smoldocling support (#14597) 6 mesi fa
  Aman Gupta 11ee0fea2a Docs: script to auto-generate ggml operations docs (#14598) 6 mesi fa
  Eric Zhang a457551332 cmake : do not search for curl libraries by ourselves (#14613) 6 mesi fa
  Akarshan Biswas 704bb7a71c SYCL: Initial set_rows kernel implementation (#14562) 6 mesi fa
  Xuan-Son Nguyen 435a6d10d6 llama : minor coding style fix for smollm3 (#14605) 6 mesi fa
  Eric Zhang f9a867f592 cmake : bump llguidance version to v1.0.1 (#14609) 6 mesi fa
  Eric Zhang ac44eb6c80 cmake : llguidance build parser library only (#14608) 6 mesi fa
  compilade a57d1bcb3c cuda : support Falcon-H1 state size for SSM_SCAN (#14602) 6 mesi fa
  Xuan-Son Nguyen cb9178f885 llama : remove llm_graph_input_one (#14603) 6 mesi fa