 Daniele
|
0a423800ff
CUDA: revert part of the RDNA1 optimizations (#8309)
|
1 سال پیش |
 Douglas Hanley
|
d12f781074
llama : streamline embeddings from "non-embedding" models (#8087)
|
1 سال پیش |
 Johannes Gäßler
|
bcefa03bc0
CUDA: fix MMQ stream-k rounding if ne00 % 128 != 0 (#8311)
|
1 سال پیش |
 Pieter Ouwerkerk
|
5a7447c569
readme : fix minor typos [no ci] (#8314)
|
1 سال پیش |
 Daniel Bevenius
|
61ecafa390
passkey : add short intro to README.md [no-ci] (#8317)
|
1 سال پیش |
 Georgi Gerganov
|
aa5898dc53
llama : prefer n_ over num_ prefix (#8308)
|
1 سال پیش |
|
Georgi Gerganov
|
6c05752c50
contributing : update guidelines (#8316)
|
1 سال پیش |
 luoyu-intel
|
a9554e20b6
[SYCL] Fix WARP_SIZE=16 bug of Intel GPU (#8266)
|
1 سال پیش |
|
Georgi Gerganov
|
e235b267a2
py : switch to snake_case (#8305)
|
1 سال پیش |
 Neo Zhang Jianyu
|
f09b7cb609
rm get_work_group_size() by local cache for performance (#8286)
|
1 سال پیش |
 Xuan Son Nguyen
|
a38b884c6c
cli: add EOT when user hit Ctrl+C (#8296)
|
1 سال پیش |
 Icecream95
|
d7fd29fff1
llama : add OpenELM support (#7359)
|
1 سال پیش |
|
Daniel Bevenius
|
6f63d646c1
tokenize : add --show-count (token) option (#8299)
|
1 سال پیش |
 ditsuke
|
51d2ebadbb
build: Export hf-to-gguf as snakecase
|
1 سال پیش |
|
ditsuke
|
1e920018d3
doc: Add context for why we add an explicit pytorch source
|
1 سال پیش |
|
ditsuke
|
01a5f06550
chore: Remove rebase artifacts
|
1 سال پیش |
|
ditsuke
|
07786a61a2
chore: Fixup requirements and build
|
1 سال پیش |
|
ditsuke
|
de14e2ea2b
chore: ignore all __pychache__
|
1 سال پیش |
|
ditsuke
|
821922916f
fix: Update script paths in CI scripts
|
1 سال پیش |
|
ditsuke
|
b1c3f26e5e
fix: Actually include scripts in build
|
1 سال پیش |
|
ditsuke
|
b0a46993df
build(python): Package scripts with pip-0517 compliance
|
1 سال پیش |
 fairydreaming
|
807b0c49ff
Inference support for T5 and FLAN-T5 model families (#5763)
|
1 سال پیش |
|
Daniel Bevenius
|
f8c4c0738d
tests : add _CRT_SECURE_NO_WARNINGS for WIN32 (#8231)
|
1 سال پیش |
|
Daniel Bevenius
|
402d6feffa
llama : suppress unref var in Windows MSVC (#8150)
|
1 سال پیش |
|
Georgi Gerganov
|
20fc3804bf
convert : fix gemma v1 tokenizer convert (#8248)
|
1 سال پیش |
 AidanBeltonS
|
f619024764
[SYCL] Remove unneeded semicolons (#8280)
|
1 سال پیش |
|
Daniele
|
d23287f122
Define and optimize RDNA1 (#8085)
|
1 سال پیش |
 slaren
|
5f2d4e60e2
ppl : fix n_seq_max for perplexity (#8277)
|
1 سال پیش |
|
Xuan Son Nguyen
|
916248af1f
fix phi 3 conversion (#8262)
|
1 سال پیش |
 Judd
|
f8d6a23804
fix typo (#8267)
|
1 سال پیش |
