Histórico de Commits

Autor SHA1 Mensagem Data
  Sam 1bdab9fdb1 llm: introduce k/v context quantization (vRAM improvements) (#6279) há 5 meses atrás
  Michael Yang d07cf41a97 refactor kv estimation há 6 meses atrás
  Michael Yang 8c238e70ab mllama cross attention há 6 meses atrás
  Patrick Devine c7cb0f0602 image processing for llama3.2 (#6963) há 6 meses atrás
  frob 09035b71cd Add missing BF16 tensor type. (#7193) há 6 meses atrás
  Michael Yang bf612cd608 Merge pull request #6260 from ollama/mxyng/mem há 8 meses atrás
  Patrick Devine 0c819e167b convert safetensor adapters into GGUF (#6327) há 8 meses atrás
  Michael Yang 6ffb5cb017 add conversion for microsoft phi 3 mini/medium 4k, 128 há 11 meses atrás
  Michael Yang 2003d60159 llama3.1 memory há 8 meses atrás
  Michael Yang 6b252918fb update convert test to check result data há 11 meses atrás
  Michael Yang 5a739ff4cb chatglm graph há 9 meses atrás
  Michael Yang de2163dafd gemma2 graph há 10 meses atrás
  Blake Mizerany cb42e607c5 llm: speed up gguf decoding by a lot (#5246) há 10 meses atrás
  Michael Yang 8e0641a9bf handle asymmetric embedding KVs há 10 meses atrás
  Michael Yang e873841cbb deepseek v2 graph há 10 meses atrás
  Daniel Hiltgen 6fd04ca922 Improve multi-gpu handling at the limit há 11 meses atrás
  Michael Yang 7bdcd1da94 Revert "Merge pull request #4938 from ollama/mxyng/fix-byte-order" há 10 meses atrás
  Michael Yang 620d5c569e fix parsing big endian gguf há 10 meses atrás
  Michael Yang 9b6c2e6eb6 detect chat template from KV há 11 meses atrás
  Michael Yang d51f15257c Update llm/ggml.go há 11 meses atrás
  Michael Yang 8f440d579a fix q5_0, q5_1 há 11 meses atrás
  Bruce MacDonald d6f692ad1a Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322) há 11 meses atrás
  Michael Yang 171eb040fc simplify safetensors reading há 11 meses atrás
  Michael Yang 1eb382da5a add phi2 mem há 11 meses atrás
  Michael Yang eeb695261f skip if same quantization há 1 ano atrás
  Michael Yang 01811c176a comments há 1 ano atrás
  Michael Yang 9685c34509 quantize any fp16/fp32 model há 1 ano atrás
  Michael Yang 435cc866a3 fix: mixtral graph há 1 ano atrás
  Michael Yang 3cf483fe48 add stablelm graph calculation há 1 ano atrás
  Michael Yang a8b9b930b4 account for all non-repeating layers há 1 ano atrás