 slaren
|
9c77ec1d74
ggml : synchronize threads using barriers (#7993)
|
1 سال پیش |
 Georgi Gerganov
|
a04a953cab
codecov : remove (#8004)
|
1 سال پیش |
 Meng, Hengyu
|
623494a478
[SYCL] refactor (#6408)
|
1 سال پیش |
 jaime-m-p
|
37bef89433
tokenizer : BPE fixes (#7530)
|
1 سال پیش |
 Sigbjørn Skjæret
|
91c188d6c2
Only use FIM middle token if it exists (#7648)
|
1 سال پیش |
 jojorne
|
84f6de17f6
Fix no gcc pragma on Windows (#7751)
|
1 سال پیش |
 Ulrich Drepper
|
61665277af
Allow compiling with CUDA without CUDA runtime installed (#7989)
|
1 سال پیش |
 Frank Mai
|
b96f9afb0d
chore: clean useless beam search param (#7985)
|
1 سال پیش |
 Abheek Gulati
|
1193778105
readme : update UI list (#7943)
|
1 سال پیش |
|
Georgi Gerganov
|
5326bcceeb
ggml : sync
|
1 سال پیش |
|
Georgi Gerganov
|
e6ecc2be47
whisper : use ggml_backend_sched (whisper/2239)
|
1 سال پیش |
 Ștefan-Gabriel Muscalu
|
a94e6ff877
update: support Qwen2-57B-A14B (#7835)
|
1 سال پیش |
 Srihari-mcw
|
5b6da18750
Make updates to type cast based on compiler instead of OS (#7851)
|
1 سال پیش |
|
Georgi Gerganov
|
7c26775adb
llama : disable FA if KV head size do not match (#7982)
|
1 سال پیش |
 Bryan Honof
|
b473e95084
Add Nix and Flox install instructions (#7899)
|
1 سال پیش |
|
slaren
|
99052cd227
sched : offload_op also requires supports_op (#7977)
|
1 سال پیش |
|
Frank Mai
|
c637fcd34d
fix: divide 0 exception in mamba (#7932)
|
1 سال پیش |
 Markus Tavenrath
|
6a2f0b3474
Implement non-mapped async IO for CUDA on Windows. (#7896)
|
1 سال پیش |
|
Georgi Gerganov
|
21be9cab94
rpc : fix load/store misaligned addresses (#7948)
|
1 سال پیش |
 Brian
|
006167aaf6
gguf-dump.py: add --markdown dump output (#7853)
|
1 سال پیش |
 Neo Zhang
|
df68d4fa5d
[SYCL] Update README-sycl.md for Chapter "Recommended release" and "News" (#7946)
|
1 سال پیش |
 Calvin Laurenson
|
43b35e38ba
Add support for sqrt on CUDA (#7953)
|
1 سال پیش |
|
Georgi Gerganov
|
19b7a836f6
cuda : fix bounds check for src0 rows in MMVQ kernel (whisper/2231)
|
1 سال پیش |
 Hong Bo PENG
|
b5fcf8ef5c
ggml : fix and optimize ppc64le (ggml/849)
|
1 سال پیش |
 Daniel Bevenius
|
398105ff43
ggml : remove duplicate include of ggml-common.h (ggml/853)
|
1 سال پیش |
|
Georgi Gerganov
|
bc6c457fa3
flake.lock: Update (#7951)
|
1 سال پیش |
|
Georgi Gerganov
|
52399254b3
unicode : avoid char32_t (#7957)
|
1 سال پیش |
 hopkins385
|
6fe1c62741
readme : update UI list [no ci] (#7958)
|
1 سال پیش |
|
Georgi Gerganov
|
cddaf028ad
ggml : fix handling of zero blocks in IQ quants (#7955)
|
1 سال پیش |
|
Georgi Gerganov
|
c8a82194a8
github : update pr template
|
1 سال پیش |
