 yummy
|
86f5623d90
llama : fix MiniCPM inference after Granite Four changes (#14850)
|
hai 5 meses |
 Molly Sophia
|
d4d1522b20
llama : add model type detection for rwkv7 7B&14B (#14816)
|
hai 6 meses |
 Georgi Gerganov
|
eacdeb5bfc
model : fix build after merge conflict (#14754)
|
hai 6 meses |
 lgai-exaone
|
e0cb5c5cb8
model : add EXAONE 4.0 support (#14630)
|
hai 6 meses |
|
Georgi Gerganov
|
8f974bc1e9
graph : refactor context to not pass gf explicitly (#14629)
|
hai 6 meses |
 Piotr Wilkin (ilintar)
|
cb887f1bc1
model: add Ernie 4.5 MoE support (#14658)
|
hai 6 meses |
|
Georgi Gerganov
|
01612b7409
llama : reuse compute graphs (#14482)
|
hai 6 meses |
 Tarek Dakhran
|
086cf81e88
llama : fix parallel processing for lfm2 (#14705)
|
hai 6 meses |
 tempstudio
|
b0f0ecc3dc
model : support output bias for qwen2 (#14711)
|
hai 6 meses |
|
Georgi Gerganov
|
225e7a1438
llama : add high-throughput mode (#14363)
|
hai 6 meses |
 Aman Gupta
|
ab14019821
Support diffusion models: Add Dream 7B (#14644)
|
hai 6 meses |
 Shunta Saito
|
e4841d24d3
llama : fix parallel processing for plamo2 (#14716)
|
hai 6 meses |
|
Shunta Saito
|
68e37a61a7
model : add PLaMo-2 support (#14560)
|
hai 6 meses |
 Tarek Dakhran
|
f5e96b368f
model : support LiquidAI LFM2 hybrid family (#14620)
|
hai 6 meses |
 Gabe Goodhart
|
0aedae00e6
model : Granite Four (#13550)
|
hai 6 meses |
 Ryan Mangeno
|
4bb625b713
Smoldocling support (#14597)
|
hai 6 meses |
 Xuan-Son Nguyen
|
cb9178f885
llama : remove llm_graph_input_one (#14603)
|
hai 6 meses |
 compilade
|
4a5686da22
llama : support Jamba hybrid Transformer-Mamba models (#7531)
|
hai 6 meses |
 Sigbjørn Skjæret
|
105554595f
llama : remove unintended whitespace (#14592)
|
hai 6 meses |
 ibrahim khadraoui
|
04655063c4
model : add support for Falcon-H1 family (#14534)
|
hai 6 meses |
|
Xuan-Son Nguyen
|
08382869a2
model : add SmolLM3 (#14581)
|
hai 6 meses |
|
Xuan-Son Nguyen
|
8f22dc0a53
model : add hunyuan moe (#14425)
|
hai 6 meses |
|
Sigbjørn Skjæret
|
e1a7059053
llama : fix incorrect minicpm3 v_states shape (#14571)
|
hai 6 meses |
|
Sigbjørn Skjæret
|
12f55c302b
llama : remove ggml_cont where possible (#14568)
|
hai 6 meses |
|
compilade
|
5d46babdc2
llama : initial Mamba-2 support (#9126)
|
hai 6 meses |
 Weizhao Ouyang
|
566c16fcce
model : add support for ERNIE 4.5 0.3B model (#14408)
|
hai 6 meses |
|
Xuan-Son Nguyen
|
8846aace49
model : gemma3n text-only (#14400)
|
hai 6 meses |
|
Sigbjørn Skjæret
|
b25346221d
llama : return mistral-v7-tekken as default template only (#14390)
|
hai 6 meses |
|
Georgi Gerganov
|
692e3cdd0a
memory : rename interface to llama_memory_context_i (#14296)
|
hai 7 meses |
|
Georgi Gerganov
|
812939a9e9
model : more uniform output id handling (#14275)
|
hai 7 meses |
