 Johannes Gäßler
|
b1f3a6e5db
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653)
|
1 месяц назад |
 Daniel Bevenius
|
444f00b0ec
llama : remove quantization sanity check (#17788)
|
1 месяц назад |
 Georgi Gerganov
|
a67ef0f47f
llama : fix sanity checks during quantization (#17721)
|
1 месяц назад |
 Piotr Wilkin (ilintar)
|
ff55414c42
model : Qwen3 Next (#16095)
|
2 месяцев назад |
 Jan Boon
|
d7395115ba
llama : use std::abs instead of abs (#16853)
|
3 месяцев назад |
 Xuan-Son Nguyen
|
3e3cb19f64
llama-quant: add support for mmproj (#16592)
|
3 месяцев назад |
 Jie Fu (傅杰)
|
745cbcf2fe
llama-quant : fix the verification of attention layers for encoder-decoder models (#16023)
|
4 месяцев назад |
 ddh0
|
df082f5630
nitpick : correct MB to MiB (#15934)
|
4 месяцев назад |
|
Xuan-Son Nguyen
|
50aa938901
convert : support non-mxfp4 HF model (#15153)
|
5 месяцев назад |
|
Georgi Gerganov
|
fd1234cb46
llama : add gpt-oss (#15091)
|
5 месяцев назад |
 Ed Addario
|
daf2dd7880
quantize : skip tensor override when in fallback mode (#14995)
|
6 месяцев назад |
|
Ed Addario
|
982e347255
quantize : fix minor logic flaw in --tensor-type (#14572)
|
6 месяцев назад |
 Tarek Dakhran
|
f5e96b368f
model : support LiquidAI LFM2 hybrid family (#14620)
|
6 месяцев назад |
|
Xuan-Son Nguyen
|
8846aace49
model : gemma3n text-only (#14400)
|
7 месяцев назад |
|
Ed Addario
|
fa4a9f2a1c
quantize : handle user-defined pruning of whole layers (blocks) (#13037)
|
7 месяцев назад |
|
Ed Addario
|
30e5b01de2
quantize : change int to unsigned int for KV overrides (#14197)
|
7 месяцев назад |
|
Ed Addario
|
e5c834f718
quantize : improve tensor-type pattern matching (#13033)
|
8 месяцев назад |
|
Johannes Gäßler
|
10d2af0eaa
llama/ggml: add LLM training support (#10544)
|
8 месяцев назад |
|
Ed Addario
|
71e90e8813
quantize: Handle user-defined quantization levels for additional tensors (#12511)
|
9 месяцев назад |
 Diego Devesa
|
e0e912f49b
llama : add option to override model tensor buffers (#11397)
|
10 месяцев назад |
 Molly Sophia
|
7dfad387e3
llama: Add support for RWKV v7 architecture (#12412)
|
10 месяцев назад |
 Xuan Son Nguyen
|
681149ced2
llama : add `llama_model_load_from_splits` (#11255)
|
1 год назад |
|
Georgi Gerganov
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
1 год назад |
|
Molly Sophia
|
ee7136c6d1
llama: add support for QRWKV6 model architecture (#11001)
|
1 год назад |
|
Georgi Gerganov
|
c07d437bbd
llama : avoid hardcoded QK_K (#11061)
|
1 год назад |
|
Johannes Gäßler
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
1 год назад |
|
Georgi Gerganov
|
5047dd3546
llama : use _impl suffix instead of _internal (#11060)
|
1 год назад |
|
Georgi Gerganov
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
1 год назад |
