Skip to content

Releases: NeoZhangJianyu/llama.cpp

b3831

28 Sep 12:28
89f9944
Compare
Choose a tag to compare
Enable use to the rebar feature to upload buffers to the device. (#9251)

b3828

27 Sep 02:57
95bc82f
Compare
Choose a tag to compare
[SYCL] add missed dll file in package (#9577)

* update oneapi to 2024.2

* use 2024.1

---------

Co-authored-by: arthw <[email protected]>

update_oneapi-b3789-3ae8374

21 Sep 08:19
Compare
Choose a tag to compare

update_oneapi-b3788-f557ccf

20 Sep 04:18
Compare
Choose a tag to compare
update oneapi to 2024.2

b3787

20 Sep 04:05
6026da5
Compare
Choose a tag to compare
server : clean-up completed tasks from waiting list (#9531)

ggml-ci

b3735

12 Sep 03:42
df4b794
Compare
Choose a tag to compare
cann: Fix error when running a non-exist op (#9424)

b3678

07 Sep 07:35
9b2c24c
Compare
Choose a tag to compare
server : simplify state machine for slot (#9283)

* server : simplify state machine for slot

* add SLOT_STATE_DONE_PROMPT

* pop_deferred_task

* add missing notify_one

* fix passkey test

* metrics : add n_busy_slots_per_decode

* fix test step

* add test

* maybe fix AddressSanitizer?

* fix deque ?

* missing lock

* pop_deferred_task: also notify

* Update examples/server/server.cpp

Co-authored-by: Georgi Gerganov <[email protected]>

---------

Co-authored-by: Georgi Gerganov <[email protected]>

b3449

24 Jul 02:48
de28008
Compare
Choose a tag to compare
examples : Fix `llama-export-lora` example (#8607)

* fix export-lora example

* add more logging

* reject merging subset

* better check

* typo

b3291

04 Jul 01:56
f619024
Compare
Choose a tag to compare
[SYCL] Remove unneeded semicolons (#8280)

b3145

14 Jun 06:10
172c825
Compare
Choose a tag to compare
rpc : fix ggml_backend_rpc_supports_buft() (#7918)