haraldwolff/llama.cpp
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity
llama.cpp/examples
History
Georgi Gerganov 2b4ea35e56
cuda : add batched cuBLAS GEMM for faster attention (#3749) 
* cmake : add helper for faster CUDA builds

* batched : add NGL arg

* ggml : skip nops in compute_forward

* cuda : minor indentation

* cuda : batched cuBLAS GEMMs for src0 F16 and src1 F32 (attention ops)

* Apply suggestions from code review

These changes plus:

```c++
#define cublasGemmBatchedEx hipblasGemmBatchedEx
```

are needed to compile with ROCM. I haven't done performance testing, but it seems to work.

I couldn't figure out how to propose a change for lines outside what the pull changed, also this is the first time trying to create a multi-part review so please forgive me if I mess something up.

* cuda : add ROCm / hipBLAS cublasGemmBatchedEx define

* cuda : add cublasGemmStridedBatchedEx for non-broadcasted cases

* cuda : reduce mallocs in cublasGemmBatchedEx branch

* cuda : add TODO for calling cublas from kernel + using mem pool

---------

Co-authored-by: Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com>
2023-10-24 16:48:37 +03:00
..
baby-llama build : enable more non-default compiler warnings (#3200) 2023-09-28 17:41:44 -04:00
batched cuda : add batched cuBLAS GEMM for faster attention (#3749) 2023-10-24 16:48:37 +03:00
batched-bench speculative : add tree-based sampling example (#3624) 2023-10-18 16:21:57 +03:00
batched.swift speculative : add tree-based sampling example (#3624) 2023-10-18 16:21:57 +03:00
beam-search llama : remove token functions with context args in favor of model (#3720) 2023-10-23 22:40:03 +03:00
benchmark benchmark-matmult : do not use integer abs() on a float (#3277) 2023-09-20 12:06:08 -04:00
convert-llama2c-to-ggml gguf : support big endian platform (#3552) 2023-10-20 14:19:40 +03:00
embedding llama.cpp : split llama_context_params into model and context params (#3301) 2023-09-28 22:42:38 +03:00
export-lora train : finetune LORA (#2632) 2023-09-28 21:40:11 +03:00
finetune ggml : add context enumeration functions (#3605) 2023-10-13 12:23:10 +02:00
gguf check C++ code with -Wmissing-declarations (#3184) 2023-09-15 15:38:27 -04:00
infill llama : remove token functions with context args in favor of model (#3720) 2023-10-23 22:40:03 +03:00
jeopardy parallel : add option to load external prompt file (#3416) 2023-10-06 16:16:38 +03:00
llama-bench llama : remove token functions with context args in favor of model (#3720) 2023-10-23 22:40:03 +03:00
llava llama : remove token functions with context args in favor of model (#3720) 2023-10-23 22:40:03 +03:00
main llama : remove token functions with context args in favor of model (#3720) 2023-10-23 22:40:03 +03:00
main-cmake-pkg cmake : fix transient definitions in find pkg (#3411) 2023-10-02 12:51:49 +03:00
metal gguf : new file format with flexible meta data (beta) (#2398) 2023-08-21 23:07:43 +03:00
parallel llama : remove token functions with context args in favor of model (#3720) 2023-10-23 22:40:03 +03:00
perplexity llama : remove token functions with context args in favor of model (#3720) 2023-10-23 22:40:03 +03:00
quantize build : enable more non-default compiler warnings (#3200) 2023-09-28 17:41:44 -04:00
quantize-stats llama.cpp : split llama_context_params into model and context params (#3301) 2023-09-28 22:42:38 +03:00
save-load-state save-load-state : fix example + add ci test (#3655) 2023-10-17 19:12:46 +03:00
server llama : remove token functions with context args in favor of model (#3720) 2023-10-23 22:40:03 +03:00
simple llama : remove token functions with context args in favor of model (#3720) 2023-10-23 22:40:03 +03:00
speculative llama : remove token functions with context args in favor of model (#3720) 2023-10-23 22:40:03 +03:00
train-text-from-scratch train-text-from-scratch : fix assert failure in ggml-alloc (#3618) 2023-10-17 20:00:58 +03:00
alpaca.sh alpaca.sh : update model file name (#2074) 2023-07-06 19:17:50 +03:00
chat-13B.bat Create chat-13B.bat (#592) 2023-03-29 20:21:09 +03:00
chat-13B.sh examples : read chat prompts from a template file (#1196) 2023-05-03 20:58:11 +03:00
chat-persistent.sh llama : fix session saving/loading (#3400) 2023-10-03 21:04:01 +03:00
chat-vicuna.sh examples : add chat-vicuna.sh (#1854) 2023-06-15 21:05:53 +03:00
chat.sh main : log file (#2748) 2023-08-30 09:29:32 +03:00
CMakeLists.txt sampling : refactor init to use llama_sampling_params (#3696) 2023-10-20 21:07:23 +03:00
gpt4all.sh examples : add -n to alpaca and gpt4all scripts (#706) 2023-04-13 16:03:39 +03:00
json-schema-to-grammar.py chmod : make scripts executable (#2675) 2023-08-23 17:29:09 +03:00
llama.vim vim : streaming and more (#2495) 2023-08-08 14:44:48 +03:00
llama2-13b.sh gitignore : changes for Poetry users + chat examples (#2284) 2023-07-21 13:53:27 +03:00
llama2.sh gitignore : changes for Poetry users + chat examples (#2284) 2023-07-21 13:53:27 +03:00
llm.vim llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879) 2023-08-30 09:50:55 +03:00
make-ggml.py make-ggml.py : compatibility with more models and GGUF (#3290) 2023-09-27 19:25:12 +03:00
Miku.sh MIKU MAYHEM: Upgrading the Default Model for Maximum Fun 🎉 (#2287) 2023-07-21 11:13:18 +03:00
reason-act.sh chmod : make scripts executable (#2675) 2023-08-23 17:29:09 +03:00
server-llama2-13B.sh chmod : make scripts executable (#2675) 2023-08-23 17:29:09 +03:00