Georgi Gerganov bcc0eb4591 llama : per-layer KV cache + quantum K cache (#4309) ...

* per-layer KV

* remove unnecessary copies

* less code duplication, offload k and v separately

* llama : offload KV cache per-layer

* llama : offload K shift tensors

* llama : offload for rest of the model arches

* llama : enable offload debug temporarily

* llama : keep the KV related layers on the device

* llama : remove mirrors, perform Device -> Host when partial offload

* common : add command-line arg to disable KV cache offloading

* llama : update session save/load

* llama : support quantum K cache (#4312)

* llama : support quantum K cache (wip)

* metal : add F32 -> Q8_0 copy kernel

* cuda : add F32 -> Q8_0 copy kernel

ggml-ci

* cuda : use mmv kernel for quantum cache ops

* llama : pass KV cache type through API

* llama : fix build

ggml-ci

* metal : add F32 -> Q4_0 copy kernel

* metal : add F32 -> Q4_1 copy kernel

* cuda : wip

* cuda : add F32 -> Q4_0 and F32 -> Q4_1 copy kernels

* llama-bench : support type_k/type_v

* metal : use mm kernel only for quantum KV cache

* cuda : add comment

* llama : remove memory_f16 and kv_f16 flags

---------

Co-authored-by: slaren <slarengh@gmail.com>

* readme : add API change notice

---------

Co-authored-by: slaren <slarengh@gmail.com>

2023-12-07 13:03:17 +02:00

..

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

ggml : add ggml_soft_max_ext (#4256)

2023-12-01 10:51:24 +02:00

batched.swift

swift : fix prompt tokenization logic (#4321)

2023-12-04 15:43:45 +02:00

beam-search

llama : remove token functions with context args in favor of model (#3720)

2023-10-23 22:40:03 +03:00

benchmark

sync : ggml (backend v2) (#3912)

2023-11-13 14:16:23 +02:00

convert-llama2c-to-ggml

gguf : support big endian platform (#3552)

2023-10-20 14:19:40 +03:00

embedding

build : link against build info instead of compiling against it (#3879)

2023-11-02 08:50:16 +02:00

export-lora

sync : ggml (backend v2) (#3912)

2023-11-13 14:16:23 +02:00

finetune

finetune - update readme to mention llama support only (#4148)

2023-11-20 19:30:00 +01:00

gguf

check C++ code with -Wmissing-declarations (#3184)

2023-09-15 15:38:27 -04:00

infill

main : Add ChatML functionality to main example (#4046)

2023-11-20 14:56:59 +01:00

jeopardy

parallel : add option to load external prompt file (#3416)

2023-10-06 16:16:38 +03:00

llama-bench

llama : per-layer KV cache + quantum K cache (#4309)

2023-12-07 13:03:17 +02:00

llama.swiftui

swift : fix concatenation method to avoid invalid UTF8 stringfication (#4325)

2023-12-04 18:03:49 +02:00

llava

llava : ShareGPT4V compatibility (vision encoder only loading) (#4172)

2023-11-30 23:11:14 +01:00

lookahead

examples : add readme files

2023-11-29 11:00:17 +02:00

main

sampling : custom samplers order (#4285)

2023-12-05 12:05:51 +02:00

main-cmake-pkg

cmake : add missed dependencies (#3763)

2023-10-24 20:48:45 +03:00

metal

sync : ggml (backend v2) (#3912)

2023-11-13 14:16:23 +02:00

parallel

llama : KV cache view API + better KV cache management (#4170)

2023-11-23 19:07:56 +02:00

perplexity

Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)

2023-11-16 19:14:37 -07:00

quantize

build : link against build info instead of compiling against it (#3879)

2023-11-02 08:50:16 +02:00

quantize-stats

llama : per-layer KV cache + quantum K cache (#4309)

2023-12-07 13:03:17 +02:00

save-load-state

build : link against build info instead of compiling against it (#3879)

2023-11-02 08:50:16 +02:00

server

llama : per-layer KV cache + quantum K cache (#4309)

2023-12-07 13:03:17 +02:00

simple

simple : update error message for KV cache check (#4324)

2023-12-04 18:04:21 +02:00

speculative

speculative : support --color (#4343)

2023-12-06 10:08:17 +02:00

tokenize

tokenize example: Respect normal add BOS token behavior (#4126)

2023-11-18 14:48:17 -07:00

train-text-from-scratch

train : fix #4227 (double free in examples/train-text-from-scratch/train-text-from-scratch.cpp) (#4351)

2023-12-07 12:25:22 +02:00

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

lookahead : add example for lookahead decoding (#4207)

2023-11-26 20:33:07 +02:00

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

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

llama.vim

vim : streaming and more (#2495)

2023-08-08 14:44:48 +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