Skip to content

Releases: ggml-org/llama.cpp

b4733

17 Feb 10:53
c4d29ba
Compare
Choose a tag to compare
server : fix divide-by-zero in metrics reporting (#11915)

b4732

17 Feb 07:26
2eea03d
Compare
Choose a tag to compare
vulkan: implement several ops relevant for ggml_opt (#11769)

* vulkan: support memset_tensor

* vulkan: support GGML_OP_SUM

* vulkan: implement GGML_OP_ARGMAX

* vulkan: implement GGML_OP_SUB

* vulkan: implement GGML_OP_COUNT_EQUAL

* vulkan: implement GGML_OP_OPT_STEP_ADAMW

* vulkan: fix check_results RWKV_WKV6 crash and memory leaks

* vulkan: implement GGML_OP_REPEAT_BACK

* tests: remove invalid test-backend-ops REPEAT_BACK tests

* vulkan: fix COUNT_EQUAL memset using a fillBuffer command

b4731

16 Feb 17:39
0f2bbe6
Compare
Choose a tag to compare
server : bump httplib to 0.19.0 (#11908)

b4730

16 Feb 10:18
fe163d5
Compare
Choose a tag to compare
common : Fix a typo in help (#11899)

This patch fixes a typo in command help.
prefx -> prefix

Signed-off-by: Masanari Iida <standby24x7@gmail.com>

b4728

16 Feb 08:18
bf42a23
Compare
Choose a tag to compare
vulkan: support multi/vision rope, and noncontiguous rope (#11902)

b4727

16 Feb 07:20
c2ea16f
Compare
Choose a tag to compare
metal : fix the crash caused by the lack of residency set support on …

b4724

15 Feb 19:09
2288510
Compare
Choose a tag to compare
metal : optimize dequant q6_K kernel (#11892)

b4722

15 Feb 15:14
68ff663
Compare
Choose a tag to compare
repo : update links to new url (#11886)

* repo : update links to new url

ggml-ci

* cont : more urls

ggml-ci

b4721

15 Feb 10:45
f355229
Compare
Choose a tag to compare
server: fix type promotion typo causing crashes w/ --jinja w/o tools …

b4720

15 Feb 08:34
fc1b0d0
Compare
Choose a tag to compare
vulkan: initial support for IQ1_S and IQ1_M quantizations (#11528)

* vulkan: initial support for IQ1_S and IQ1_M quantizations

* vulkan: define MMV kernels for IQ1 quantizations

* devops: increase timeout of Vulkan tests again

* vulkan: simplify ifdef for init_iq_shmem