Skip to content

Releases: ggml-org/llama.cpp

b5311

08 May 13:04
51fb96b
Compare
Choose a tag to compare
context : remove logits_all flag (#13284)

* context : remove logits_all flag

ggml-ci

* llama : remove logits_all flag + reorder llama_context_params

ggml-ci

b5310

08 May 12:57
70a6991
Compare
Choose a tag to compare
ci : move release workflow to a separate file (#13362)

b5309

08 May 15:03
f061021
Compare
Choose a tag to compare
llama : print size and type of overridden tensors (#13364)

b5308

08 May 09:57
8733e0c
Compare
Choose a tag to compare
sycl: addressing non-contiguous src1 mul_mats (nc and batched) (#13343)

* sycl: fixed non-contiguous src1 mul_mats (nc and batched)

* Fixed wrong static_cast inside kernel

b5306

07 May 17:11
Compare
Choose a tag to compare
sync : ggml

ggml-ci

b5303

07 May 12:56
bc4e112
Compare
Choose a tag to compare
llama : deci : support ffn-free with attention (#13296)

b5302

07 May 10:50
39e73ae
Compare
Choose a tag to compare
common : Add a warning when we can't match samplers from a string or …

b5301

07 May 10:32
1f73301
Compare
Choose a tag to compare
cuda : remove nrows_x in mul_mat_q_process_tile (#13325)

Signed-off-by: Xiaodong Ye <[email protected]>

b5300

07 May 10:11
4773d7a
Compare
Choose a tag to compare
examples : remove infill (#13283)

ggml-ci

b5299

07 May 09:16
6c7fd67
Compare
Choose a tag to compare
llama : support tie embedding for chatglm models (#13328)