ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
llama.cpp/examples
History
HimariO ca2bb89eac
clip : Add Qwen2.5VL support (#12402) 
* implment vision model architecture, gguf convertor

* handle window attention inputs

* add debug utils

* fix few incorrect tensor memory layout

* move position id remap out of ggml to avoid int32 cuda operations

* cleaning up

* ignore transformers Qwen2_5_xxx type check

* remove not so often use `qwen2vl-cli` debug functions

* remove commented-out code blocks

* fix attn weight scaling after rebase

* add `PROJECTOR_TYPE_QWEN2_5_VL`

* remove `KEY_USE_GLU_MLP`, `KEY_USE_RMS_NORM`

* replace `KEY_FULLATTN_BLK_IDX` with `KEY_WIN_ATTN_PATTERN`

* remove `attn_window_size` from gguf

* fix model conversion

* clean up

* fix merging problem

* add test

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
2025-04-27 10:10:34 +02:00
..
batched common : refactor downloading system, handle mmproj with -hf option (#12694) 2025-04-01 23:44:05 +02:00
batched-bench common : refactor downloading system, handle mmproj with -hf option (#12694) 2025-04-01 23:44:05 +02:00
batched.swift llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 2025-03-13 12:35:44 +02:00
convert-llama2c-to-ggml llama : add llama_vocab, functions -> methods, naming (#11110) 2025-01-12 11:32:42 +02:00
cvector-generator llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 2025-03-13 12:35:44 +02:00
deprecation-warning Update deprecation-warning.cpp (#10619) 2024-12-04 23:19:20 +01:00
embedding embeddings : fix batch sizes (#13076) 2025-04-24 22:29:22 +03:00
eval-callback llama : add llama_vocab, functions -> methods, naming (#11110) 2025-01-12 11:32:42 +02:00
export-lora common : refactor downloading system, handle mmproj with -hf option (#12694) 2025-04-01 23:44:05 +02:00
gen-docs ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
gguf GGUF: C++ refactor, backend support, misc fixes (#11030) 2025-01-07 18:01:58 +01:00
gguf-hash GGUF: C++ refactor, backend support, misc fixes (#11030) 2025-01-07 18:01:58 +01:00
gguf-split gguf-split : --merge now respects --dry-run option (#12681) 2025-04-04 16:09:12 +02:00
gritlm common : refactor downloading system, handle mmproj with -hf option (#12694) 2025-04-01 23:44:05 +02:00
imatrix llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 2025-03-13 12:35:44 +02:00
infill llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 2025-03-13 12:35:44 +02:00
jeopardy build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
llama-bench llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 2025-03-13 12:35:44 +02:00
llama.android cmake : enable curl by default (#12761) 2025-04-07 13:35:19 +02:00
llama.swiftui llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 2025-03-13 12:35:44 +02:00
llava clip : Add Qwen2.5VL support (#12402) 2025-04-27 10:10:34 +02:00
lookahead llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 2025-03-13 12:35:44 +02:00
lookup llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 2025-03-13 12:35:44 +02:00
main main : Fix Ctrl+D/newline handling (#12951) 2025-04-18 22:02:55 +02:00
parallel llama : refactor kv cache guard (#12695) 2025-04-02 14:32:59 +03:00
passkey common : refactor downloading system, handle mmproj with -hf option (#12694) 2025-04-01 23:44:05 +02:00
perplexity hellaswag: display estimated score confidence interval (#12797) 2025-04-07 18:47:08 +03:00
quantize quantize: Handle user-defined quantization levels for additional tensors (#12511) 2025-04-13 21:29:28 +03:00
retrieval llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 2025-03-13 12:35:44 +02:00
rpc rpc : add command line option for number of threads for the CPU backend (#13060) 2025-04-23 10:32:49 +03:00
run contrib: support modelscope community (#12664) 2025-04-11 14:01:56 +02:00
save-load-state llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 2025-03-13 12:35:44 +02:00
server grammar : handle maxItems == 0 in JSON schema (#13117) 2025-04-26 10:10:20 +02:00
simple llama : add llama_vocab, functions -> methods, naming (#11110) 2025-01-12 11:32:42 +02:00
simple-chat llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181) 2025-03-13 12:35:44 +02:00
simple-cmake-pkg repo : update links to new url (#11886) 2025-02-15 16:40:57 +02:00
speculative common : refactor downloading system, handle mmproj with -hf option (#12694) 2025-04-01 23:44:05 +02:00
speculative-simple common : refactor downloading system, handle mmproj with -hf option (#12694) 2025-04-01 23:44:05 +02:00
sycl dsiable curl lib check, this action is missed by commit bd3f59f812 (#12761) (#12937) 2025-04-14 18:19:07 +08:00
tokenize llama : add llama_vocab, functions -> methods, naming (#11110) 2025-01-12 11:32:42 +02:00
tts common : refactor downloading system, handle mmproj with -hf option (#12694) 2025-04-01 23:44:05 +02:00
chat-13B.bat Create chat-13B.bat (#592) 2023-03-29 20:21:09 +03:00
chat-13B.sh build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
chat-persistent.sh scripts : fix pattern and get n_tokens in one go (#10221) 2024-11-09 09:06:54 +02:00
chat-vicuna.sh build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
chat.sh build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
CMakeLists.txt cmake : do not include ./src as public for libllama (#13062) 2025-04-24 16:00:10 +03:00
convert_legacy_llama.py metadata: Detailed Dataset Authorship Metadata (#8875) 2024-11-13 21:10:38 +11:00
json_schema_pydantic_example.py py : type-check all Python scripts with Pyright (#8341) 2024-07-07 15:04:39 -04:00
json_schema_to_grammar.py grammar : handle maxItems == 0 in JSON schema (#13117) 2025-04-26 10:10:20 +02:00
llama.vim repo : update links to new url (#11886) 2025-02-15 16:40:57 +02:00
llm.vim llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879) 2023-08-30 09:50:55 +03:00
Miku.sh build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
pydantic_models_to_grammar.py pydantic : replace uses of __annotations__ with get_type_hints (#8474) 2024-07-14 19:51:21 -04:00
pydantic_models_to_grammar_examples.py repo : update links to new url (#11886) 2025-02-15 16:40:57 +02:00
reason-act.sh build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
regex_to_grammar.py py : switch to snake_case (#8305) 2024-07-05 07:53:33 +03:00
server-llama2-13B.sh build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809) 2024-06-13 00:41:52 +01:00
server_embd.py llama : fix FA when KV cache is not used (i.e. embeddings) (#12825) 2025-04-08 19:54:51 +03:00
ts-type-to-grammar.sh JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555) 2024-04-12 19:43:38 +01:00