 Ed Addario
|
982e347255
quantize : fix minor logic flaw in --tensor-type (#14572)
|
пре 6 месеци |
 Tarek Dakhran
|
f5e96b368f
model : support LiquidAI LFM2 hybrid family (#14620)
|
пре 6 месеци |
 Xuan-Son Nguyen
|
8846aace49
model : gemma3n text-only (#14400)
|
пре 6 месеци |
|
Ed Addario
|
fa4a9f2a1c
quantize : handle user-defined pruning of whole layers (blocks) (#13037)
|
пре 6 месеци |
|
Ed Addario
|
30e5b01de2
quantize : change int to unsigned int for KV overrides (#14197)
|
пре 7 месеци |
|
Ed Addario
|
e5c834f718
quantize : improve tensor-type pattern matching (#13033)
|
пре 8 месеци |
 Johannes Gäßler
|
10d2af0eaa
llama/ggml: add LLM training support (#10544)
|
пре 8 месеци |
|
Ed Addario
|
71e90e8813
quantize: Handle user-defined quantization levels for additional tensors (#12511)
|
пре 9 месеци |
 Diego Devesa
|
e0e912f49b
llama : add option to override model tensor buffers (#11397)
|
пре 9 месеци |
 Molly Sophia
|
7dfad387e3
llama: Add support for RWKV v7 architecture (#12412)
|
пре 10 месеци |
 Xuan Son Nguyen
|
681149ced2
llama : add `llama_model_load_from_splits` (#11255)
|
пре 1 година |
 Georgi Gerganov
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
пре 1 година |
|
Molly Sophia
|
ee7136c6d1
llama: add support for QRWKV6 model architecture (#11001)
|
пре 1 година |
|
Georgi Gerganov
|
c07d437bbd
llama : avoid hardcoded QK_K (#11061)
|
пре 1 година |
|
Johannes Gäßler
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
пре 1 година |
|
Georgi Gerganov
|
5047dd3546
llama : use _impl suffix instead of _internal (#11060)
|
пре 1 година |
|
Georgi Gerganov
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
пре 1 година |
