llama.cpp

profiler: initial support for profiling graph ops

#1574:Commit d4051c81ee pushed by root

graph-profiler

2024-12-25 02:44:36 +00:00

0s

llama : support InfiniAI Megrez 3b (#10893)

#1562:Commit b92a14a841 pushed by root

b4381

2024-12-24 14:44:32 +00:00

0s

llama : support for Llama-3_1-Nemotron-51B (#10669)

#1560:Commit 6f0c9e034b pushed by root

b4380

2024-12-24 14:44:32 +00:00

0s

rebase

#1558:Commit de014bc339 pushed by root

gg/llama-refactor-0

2024-12-24 14:44:32 +00:00

0s

llama : add Falcon3 support (#10883)

#1555:Commit 7ae33a616f pushed by root

b4376

2024-12-24 02:44:32 +00:00

0s

llama : support InfiniAI Megrez 3b (#10893)

#1552:Commit b92a14a841 pushed by root

master

2024-12-24 02:44:32 +00:00

0s

convert : add BertForMaskedLM (#10919)

#1546:Commit 5cd85b5e00 pushed by root

master

2024-12-22 14:44:32 +00:00

0s

convert : fix RWKV v6 model conversion (#10913)

#1542:Commit 0a11f8b7b5 pushed by root

b4368

2024-12-21 20:44:32 +00:00

0s

SYCL: Migrate away from deprecated ggml_tensor->backend (#10840)

#1539:Commit eb5c3dc64b pushed by root

master

2024-12-21 08:54:36 +00:00

0s

convert : add BertForMaskedLM

#1537:Commit 564c23b8fd pushed by root

gg/bert-add-variant

2024-12-21 20:44:32 +00:00

0s

llama : fix Roberta embeddings (#10856)

#1533:Commit 2fffc52b50 pushed by root

b4362

2024-12-20 20:44:32 +00:00

0s

convert : Add support for Microsoft Phi-4 model (#10817)

#1531:Commit 7585edbdeb pushed by root

b4361

2024-12-20 20:44:32 +00:00

0s

llama : minor grammar refactor (#10897)

#1528:Commit 5cab3e4aaa pushed by root

master

2024-12-20 16:34:36 +00:00

0s

ggml : fix arm build (#10890)

#1523:Commit 9177484f58 pushed by root

master

2024-12-19 16:04:37 +00:00

0s

Revert "llama : add Falcon3 support (#10864)" (#10876)

#1516:Commit 4da69d1abd pushed by root

b4351

2024-12-19 08:44:32 +00:00

0s

Revert "llama : add Falcon3 support (#10864)" (#10876)

#1513:Commit 4da69d1abd pushed by root

master

2024-12-18 23:44:35 +00:00

0s

llama : add Falcon3 support (#10864)

#1508:Commit 382bc7f2e8 pushed by root

b4341

2024-12-19 02:44:32 +00:00

0s

Revert "llama : add Falcon3 support (#10864)"

#1506:Commit e10dc009b5 pushed by root

revert-10864-falcon3_integration

2024-12-19 02:44:32 +00:00

0s

Use model->gguf_kv for loading the template instead of using the C API. (#10868)

#1503:Commit d62b532c52 pushed by root

master

2024-12-18 07:24:36 +00:00

0s

tts : extend python example to generate spectrogram

#1500:Commit 265a5eac5a pushed by root

gg/tts-add-outetts

2024-12-18 20:44:32 +00:00

0s

tts : outetts-voc -> wavtokenizer-dec

#1496:Commit 985d59f5e5 pushed by root

gg/tts-add-outetts

2024-12-17 14:44:32 +00:00

0s

llama : add Deepseek MoE v1 & GigaChat models (#10827)

#1492:Commit a0974156f3 pushed by root

b4333

2024-12-17 02:44:32 +00:00

0s

llava : Allow locally downloaded models for QwenVL (#10833)

#1489:Commit 4ddd199f6f pushed by root

master

2024-12-17 02:44:32 +00:00

0s

llama : add Qwen2VL support + multimodal RoPE (#10361)

#1479:Commit ba1cb19cdd pushed by root

b4327

2024-12-15 14:44:32 +00:00

0s

llama : add Qwen2VL support + multimodal RoPE (#10361)

#1476:Commit ba1cb19cdd pushed by root

master

2024-12-15 14:44:32 +00:00

0s

lora : warn user if new token is added in the adapter (#9948)

#1457:Commit c421ac072d pushed by root

b3959

2024-12-13 14:09:49 +00:00

0s

convert : identify missing model files (#9397)

#1448:Commit d54c21df7e pushed by root

b3769

2024-12-13 14:09:49 +00:00

0s

py : add "LLaMAForCausalLM" conversion support (#9485)

#1445:Commit 3c7989fd29 pushed by root

b3758

2024-12-13 14:09:49 +00:00

0s

lora : fix llama conversion script with ROPE_FREQS (#9117)

#1432:Commit 3ba780e2a8 pushed by root

b3618

2024-12-13 14:09:49 +00:00

0s

convert-*.py: remove add_name from ChatGLMModel class (#8590)

#1415:Commit 57b1d4f9eb pushed by root

b3422

2024-12-13 14:09:49 +00:00

0s