 Xuan Son Nguyen
|
46110e0630
split q_proj/gate
|
4 months ago |
 Piotr Wilkin (ilintar)
|
c78f9fce68
Merge branch 'ggml-org:master' into qwen3_next
|
4 months ago |
|
Piotr Wilkin
|
344331c2b6
First draft
|
4 months ago |
|
Xuan-Son Nguyen
|
8f8f2274ee
convert : add Llama4ForCausalLM (#16042)
|
4 months ago |
 Daniel Bevenius
|
2c8dac72eb
llama : fix incorrect model type for Gemma 270M (#15764)
|
4 months ago |
 Sigbjørn Skjæret
|
84ab83cc0b
model : jina-embeddings-v3 support (#13693)
|
5 months ago |
|
Piotr Wilkin (ilintar)
|
b1afcab804
model : add support for Seed-OSS (#15490)
|
5 months ago |
 Georgi Gerganov
|
9ef6b0b835
model : add gpt-oss type strings (#15424)
|
5 months ago |
|
Daniel Bevenius
|
7a0de96045
llama : add 18-layer model type for Gemma 3-270m (#15319)
|
5 months ago |
|
Georgi Gerganov
|
fd1234cb46
llama : add gpt-oss (#15091)
|
5 months ago |
 Sam
|
ef0144c087
model: support GLM 4.5 family of models (#14939)
|
5 months ago |
|
Piotr Wilkin (ilintar)
|
cb887f1bc1
model: add Ernie 4.5 MoE support (#14658)
|
6 months ago |
|
Georgi Gerganov
|
01612b7409
llama : reuse compute graphs (#14482)
|
6 months ago |
 Tarek Dakhran
|
f5e96b368f
model : support LiquidAI LFM2 hybrid family (#14620)
|
6 months ago |
 Ryan Mangeno
|
4bb625b713
Smoldocling support (#14597)
|
6 months ago |
 compilade
|
4a5686da22
llama : support Jamba hybrid Transformer-Mamba models (#7531)
|
6 months ago |
|
Xuan-Son Nguyen
|
8f22dc0a53
model : add hunyuan moe (#14425)
|
6 months ago |
|
compilade
|
5d46babdc2
llama : initial Mamba-2 support (#9126)
|
7 months ago |
 Weizhao Ouyang
|
566c16fcce
model : add support for ERNIE 4.5 0.3B model (#14408)
|
7 months ago |
|
Xuan-Son Nguyen
|
8846aace49
model : gemma3n text-only (#14400)
|
7 months ago |
 Mikko Juola
|
9ae4143bc6
model : add dots.llm1 architecture support (#14044) (#14118)
|
7 months ago |
|
Sigbjørn Skjæret
|
d17a809ef0
llama : support multiple classifier outputs and labels (#13940)
|
7 months ago |
|
Georgi Gerganov
|
e298d2fbd0
kv-cache : add SWA support (#13194)
|
8 months ago |
 Johannes Gäßler
|
10d2af0eaa
llama/ggml: add LLM training support (#10544)
|
8 months ago |
 ymcki
|
3bf785f3ef
llama : Llama-3_1-Nemotron-Ultra-253B-v1 support (#12843)
|
9 months ago |
|
Georgi Gerganov
|
c642bc014c
kv-cache : separate recurrent vs non-recurrent impl (#12799)
|
9 months ago |
 Jared Van Bortel
|
a70183eb00
llama-model : fix the reported size class for nomic-embed-text-v2-moe (#13223)
|
9 months ago |
|
Sigbjørn Skjæret
|
7d3af70b08
llama : llm_type order by size (#13177)
|
9 months ago |
|
Sigbjørn Skjæret
|
e98b3692be
llama : set qwen3 model type sizes (#13175)
|
9 months ago |
 Juk Armstrong
|
daa422881a
llama : DeepSeek V2/V3 MLA implementation (#12801)
|
9 months ago |
