Skip to content

Releases: dumpmemory/llama.cpp

b5907

16 Jul 09:20
@github-actions github-actions
b5907
5cae766
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b5907 Latest
Latest 
scripts: synthetic prompt mode for server-bench.py (#14695)
Assets 15

b5903

16 Jul 04:05
@github-actions github-actions
b5903
c81f419
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b5903 
gguf-py : dump bpw per layer and model in markdown mode (#14703)
Loading

b5900

15 Jul 23:11
@github-actions github-actions
b5900
10a0351
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b5900 
vulkan: add RTE variants for glu/add/sub/mul/div (#14653)
Loading

b5898

15 Jul 09:34
@github-actions github-actions
b5898
cbc68be
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b5898 
cuda: fix build warnings in set-rows.cu (unused variable) (#14687)

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
Loading

b5585

04 Jun 08:50
@github-actions github-actions
b5585
0b4be4c
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b5585 
CUDA: fix FTZ in FA for Gemma 3 (#13991)
Loading

b5581

03 Jun 02:50
@github-actions github-actions
b5581
71e74a3
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b5581 
opencl: add `backend_synchronize` (#13939)

* This is not needed by the normal use where the result is read
  using `tensor_get`, but it allows perf mode of `test-backend-ops`
  to properly measure performance.
Loading

b5579

02 Jun 21:11
@github-actions github-actions
b5579
3637576
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b5579 
server : disable speculative decoding for SWA models (#13970)

* server : use swa-full fo draft context

ggml-ci

* server : disable speculative decoding for SWA models
Loading

b5574

02 Jun 14:25
@github-actions github-actions
b5574
093e3f1
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b5574 
cmake : Handle mixed-case 'Power' strings in POWER CPU detection (#13…
Loading

b5568

01 Jun 15:15
@github-actions github-actions
b5568
f3a4b16
Compare
Choose a tag to compare
b5568 
sync : ggml

ggml-ci
Loading

b5558

01 Jun 03:58
@github-actions github-actions
b5558
053b153
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
b5558 
threading: support for GGML_SCHED_PRIO_LOW, update thread info on Win…
Loading