Minsoo Cheong 6d341ab6c5 speculative : implement stochastic speculative sampling (#5625) ...

* (WIP) Implement stochastic speculative decoding

* sample from residual distribution on draft accept failure

* fix #5657: force greedy sampling with probs when temp is 0

* remove p_accept parameter

* fix style

* remove unused variables

* add srand() in speculative.cpp

* replace use of rand() with mt19937 sampling

* fixes based on review (@JohannesGaessler)

* fix r random generation

* randomly select next sequence to verify + fix bug in memory freeing

* fix bug in active_seqs sync

* fix uniform int distribution initialization

* remove warnings from comparison between int and size_t

* check grammar in `llama_sample_probability_distribution_impl`

* remove malloc code by utilizing vectors

* add PR link to README

2024-03-04 20:24:00 +02:00

..

baby-llama

code : normalize enum names (#5697)

2024-02-25 12:09:09 +02:00

batched

ggml, common, examples, tests : fixed type arguments in printf (#5528)

2024-02-18 18:20:12 +02:00

batched-bench

llama : cleanup unused mmq flags (#5772)

2024-03-01 13:39:06 +02:00

batched.swift

ggml : add numa options (#5377)

2024-02-16 11:31:07 +02:00

beam-search

ggml : add numa options (#5377)

2024-02-16 11:31:07 +02:00

benchmark

2-bit quantizations (#4897)

2024-01-14 09:45:56 +02:00

convert-llama2c-to-ggml

ggml, common, examples, tests : fixed type arguments in printf (#5528)

2024-02-18 18:20:12 +02:00

embedding

ggml : add numa options (#5377)

2024-02-16 11:31:07 +02:00

export-lora

ci : add an option to fail on compile warning (#3952)

2024-02-17 23:03:14 +02:00

finetune

code : normalize enum names (#5697)

2024-02-25 12:09:09 +02:00

gguf

gguf : simplify example dependencies

2023-12-21 23:08:14 +02:00

imatrix

ggml : add numa options (#5377)

2024-02-16 11:31:07 +02:00

infill

convert : automatically fall back to HfVocab if tokenizer.model doesn't exist (#5821)

2024-03-02 12:27:26 -05:00

jeopardy

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

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

llama-bench

Support multiple GPUs (split mode) on SYCL backend (#5806)

2024-03-02 19:49:30 +08:00

llama.android

ggml-quants : provide ggml_vqtbl1q_u8 for 64bit compatibility (#5711)

2024-02-25 20:43:00 +02:00

llama.swiftui

ggml : add numa options (#5377)

2024-02-16 11:31:07 +02:00

llava

code : normalize enum names (#5697)

2024-02-25 12:09:09 +02:00

lookahead

ggml : add numa options (#5377)

2024-02-16 11:31:07 +02:00

lookup

ggml : add numa options (#5377)

2024-02-16 11:31:07 +02:00

main

main : support special tokens as reverse/anti prompt (#5847)

2024-03-04 09:57:20 +02:00

main-cmake-pkg

main-cmake-pkg : fix build issue (#4665)

2023-12-29 16:18:20 +02:00

parallel

ggml : add numa options (#5377)

2024-02-16 11:31:07 +02:00

passkey

llama : fix defrag bugs + add parameter (#5735)

2024-02-27 14:35:51 +02:00

perplexity

ci : fix wikitext url + compile warnings (#5569)

2024-02-18 22:39:30 +02:00

quantize

IQ4_XS: a 4.25 bpw quantization (#5747)

2024-02-27 16:34:24 +02:00

quantize-stats

refactor : switch to emplace_back to avoid extra object (#5291)

2024-02-03 13:23:37 +02:00

save-load-state

llama : minimize size used for state save/load (#4820)

2024-01-13 18:29:43 +02:00

server

add alias for chat template (#5858)

2024-03-04 12:22:08 +01:00

simple

ggml : add numa options (#5377)

2024-02-16 11:31:07 +02:00

speculative

speculative : implement stochastic speculative sampling (#5625)

2024-03-04 20:24:00 +02:00

sycl

Support multiple GPUs (split mode) on SYCL backend (#5806)

2024-03-02 19:49:30 +08:00

tokenize

ggml : add numa options (#5377)

2024-02-16 11:31:07 +02:00

train-text-from-scratch

code : normalize enum names (#5697)

2024-02-25 12:09:09 +02:00

alpaca.sh

alpaca.sh : update model file name (#2074)

2023-07-06 19:17:50 +03:00

base-translate.sh

examples : improve base-translate.sh script (#4783)

2024-01-06 11:40:24 +02:00

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

gguf : add python reader example (#5216)

2024-02-13 19:56:38 +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

examples : support minItems/maxItems in JSON grammar converter (#5039)

2024-02-19 16:14:07 +02:00

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

llama.vim : added api key support (#5090)

2024-01-23 08:51:27 +02:00

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

pydantic_models_to_grammar.py

examples : make pydantic scripts pass mypy and support py3.8 (#5099)

2024-01-25 14:51:24 -05:00

pydantic-models-to-grammar-examples.py

examples : make pydantic scripts pass mypy and support py3.8 (#5099)

2024-01-25 14:51:24 -05:00

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