root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 03:14:35 +00:00
Code Issues Actions 7 Packages Projects Releases Wiki Activity
e52aba537a
llama.cpp/examples
History
HimariO ba1cb19cdd
Some checks failed
flake8 Lint / Lint (push) Waiting to run
Details
Python Type-Check / pyright type-check (push) Waiting to run
Details
Python check requirements.txt / check-requirements (push) Has been cancelled
Details
llama : add Qwen2VL support + multimodal RoPE (#10361) 
* Barebone Qwen2VL LLM convertor

* Add Qwen2VL cli entrypoint

* [WIP] add qwen2vl arch

* Verify m-rope output

* Add vl-rope/2d-rope support for qwen2vl ViT

* update qwen2vl cli tool

* update 5D tensor op workaround

* [WIP] qwen2vl vision model

* make batch and clip utils compatible with qwen2vl

* [WIP] create inference workflow, gguf convert script but fix

* correcting vision-rope behavior, add the missing last layer back to ViT

* add arg parser to qwen2vl_surgery

* replace variable size array with vector

* cuda-gdb cmake preset

* add fp32 mrope, vision rope kernel

* add fp16 support for qwen2vl and m-rope

* add `GGML_ROPE_TYPE_MROPE`, `GGML_ROPE_TYPE_VISION`

* fix rope op mode switching, out dated func args

* update `llama_hparams`

* update to keep up stream changes

* resolve linter, test errors

* add makefile entry, update speical image padding token

* add mrope unit test, fix few compiler warnings

* rename `mrope` related function, params

* minor updates on debug util, bug fixs

* add `m-rope` testcase to `test-backend-ops`

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* fix traililng whitespce

* store `llama_hparams.rope_sections` with fixed size array

* update position id tensor size check in GGML_OP_ROPE

* minor updates

* update `ggml_backend_*_supports_op` of unsupported backends

* remote old `rope_section` compare operator

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-12-14 14:43:46 +02:00
..
batched ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
batched-bench ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
batched.swift llama : llama_perf + option to disable timings during decode (#9355) 2024-09-13 09:53:38 +03:00
convert-llama2c-to-ggml make : deprecate (#10514) 2024-12-02 21:22:53 +02:00
cvector-generator ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
deprecation-warning Update deprecation-warning.cpp (#10619) 2024-12-04 23:19:20 +01:00
embedding ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
eval-callback ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
export-lora ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
gbnf-validator ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
gen-docs ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
gguf ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
gguf-hash ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
gguf-split remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797) 2024-12-12 19:02:49 +01:00
gritlm ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
imatrix make : deprecate (#10514) 2024-12-02 21:22:53 +02:00
infill readme : add option, update default value, fix formatting (#10271) 2024-12-03 12:50:08 +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 remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797) 2024-12-12 19:02:49 +01:00
llama.android llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745) 2024-10-18 23:18:01 +02:00
llama.swiftui llama : use cmake for swift build (#10525) 2024-12-08 13:14:54 +02:00
llava llama : add Qwen2VL support + multimodal RoPE (#10361) 2024-12-14 14:43:46 +02:00
lookahead ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
lookup ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
main readme : add option, update default value, fix formatting (#10271) 2024-12-03 12:50:08 +02:00
main-cmake-pkg ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
parallel ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
passkey ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
perplexity ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
quantize Update README.md (#10772) 2024-12-11 16:16:32 +01:00
quantize-stats ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
retrieval remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797) 2024-12-12 19:02:49 +01:00
rpc ggml : move CPU backend to a separate file (#10144) 2024-11-03 19:34:08 +01:00
run Opt class for positional argument handling (#10508) 2024-12-13 19:34:25 +01:00
save-load-state ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
server Removes spurious \r in output that causes logging in journalctl to treat lines as binary and therefore hidden by default (#10771) 2024-12-13 23:21:49 +01:00
simple ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
simple-chat ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
speculative ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
speculative-simple ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
sycl [SYCL]set context default value to avoid memory issue, update guide (#9476) 2024-09-18 08:30:31 +08:00
tokenize remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797) 2024-12-12 19:02:49 +01:00
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 common : improve -ctv -ctk CLI arguments (#10806) 2024-12-12 22:53:05 +01:00
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 : fix JSON Schema for string regex with top-level alt. (#9903) 2024-10-16 19:03:24 +03:00
llama.vim llama.vim : bump generation time limit to 3s [no ci] 2024-10-23 17:16:56 +03:00
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_examples.py examples : Rewrite pydantic_models_to_grammar_examples.py (#8493) 2024-07-20 22:09:17 -04:00
pydantic_models_to_grammar.py pydantic : replace uses of __annotations__ with get_type_hints (#8474) 2024-07-14 19:51:21 -04:00
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_embd.py py : type-check all Python scripts with Pyright (#8341) 2024-07-07 15:04:39 -04:00
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
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