Skip to content

Releases: ggml-org/llama.cpp

b4778

25 Feb 16:06
a82c9e7
Compare
Choose a tag to compare
vulkan: fix assertion when qy_needs_dequant (#12068)

Looks like a copy/paste bug from qx_needs_dequant.

b4777

25 Feb 13:21
401af80
Compare
Choose a tag to compare
server: handle echo=false on /v1/completions (#12060)

b4776

25 Feb 13:16
c132239
Compare
Choose a tag to compare
add OP sigmoid (#12056)

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

b4775

25 Feb 13:15
393fca6
Compare
Choose a tag to compare
ggml-cpu: Fix build with sve (#12059)

* ggml-cpu: Fix build with sve

Signed-off-by: Molly Sophia <[email protected]>

* ggml-cpu: Remove unused variable in sve q3_k vec dot

Signed-off-by: Molly Sophia <[email protected]>

---------

Signed-off-by: Molly Sophia <[email protected]>

b4774

25 Feb 12:56
61d4f39
Compare
Choose a tag to compare
vulkan: implement more backpropagation operators (#11914)

* vulkan: implement GGML_OP_ROPE_BACK

* vulkan: implement GGML_OP_RMS_NORM_BACK

* vulkan: implement GGML_OP_SILU_BACK

* vulkan: implement GGML_OP_SOFTMAX_BACK

b4773

25 Feb 11:29
0b52745
Compare
Choose a tag to compare
server: support add_generation_prompt query param (#12062)

b4771

25 Feb 10:21
3e9a286
Compare
Choose a tag to compare
llama : expose llama_model_n_head_kv in the API (#11997)

It's useful to be able to have this from the library layer as it's a key
parameter of the model (e.g. to figure out how much KV cache memory is
needed).

b4770

25 Feb 10:15
58d07a8
Compare
Choose a tag to compare
metal : copy kernels for quant to F32/F16 conversions (#12017)

metal: use dequantize_q templates

---------

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

b4769

24 Feb 22:23
34a846b
Compare
Choose a tag to compare
opencl: fix for small models (#11950)

* opencl: fix small shape gemv, remove unused extensions

* opencl: fix `transpose_16`, `dump_tensor`, enforce subgroup size

* opencl: fix for token length < 4

* opencl: use wave size of 64 for all Adreno GPUs

---------

Co-authored-by: Shawn Gu <[email protected]>
Co-authored-by: Skyler Szot <[email protected]>

b4768

24 Feb 16:54
7a2c913
Compare
Choose a tag to compare
llava : Add Granite Vision Support (#11794)

* Add super wip scripts for multimodal granite gguf

Signed-off-by: Alex-Brooks <[email protected]>

* Add example for converting mmgranite to gguf

Signed-off-by: Alex-Brooks <[email protected]>

* remove hardcoded path

Signed-off-by: Alex-Brooks <[email protected]>

* Add vision feature layer to gguf params

Signed-off-by: Alex-Brooks <[email protected]>

* Clean up llava surgery and remove name substitution hacks

Signed-off-by: Alex-Brooks <[email protected]>

* Add transformers llava next tensor name mapping

Signed-off-by: Alex-Brooks <[email protected]>

* Make siglip / openclip mutuall exclusive

Signed-off-by: Alex-Brooks <[email protected]>

* Fix projector linear substitution

Signed-off-by: Alex-Brooks <[email protected]>

* Fix linear 2 substitution index

Signed-off-by: Alex-Brooks <[email protected]>

* Increase max flattened gridpoints to 64

Signed-off-by: Alex-Brooks <[email protected]>

* Fix hardcoded concat for multiple feature layers

Signed-off-by: Alex-Brooks <[email protected]>

* Pull vision feature layers out of gguf keys

Signed-off-by: Alex-Brooks <[email protected]>

* fix num gridpoints and use all layers

Signed-off-by: Alex-Brooks <[email protected]>

* Avoid dropping last image encoder layer in llava models

Signed-off-by: Alex-Brooks <[email protected]>

* Use 10 for max number of patches

Signed-off-by: Alex-Brooks <[email protected]>

* Standardize vision feature layers

Signed-off-by: Alex-Brooks <[email protected]>

* Cleanup logs

Signed-off-by: Alex-Brooks <[email protected]>

* Update comment for vision feature layer init

Signed-off-by: Alex-Brooks <[email protected]>

* Update notes for alternative to legacy llm conversion script

Signed-off-by: Alex-Brooks <[email protected]>

* Fix notes rendering

Signed-off-by: Alex-Brooks <[email protected]>

* Add v prefix to vision feature layer log

Signed-off-by: Alex-Brooks <[email protected]>

* Use current defaults for feature layer

Signed-off-by: Alex-Brooks <[email protected]>

* Use constant for max gridpoints / feat layers, style fixes

Signed-off-by: Alex-Brooks <[email protected]>

* clarify non-negative feature layers

Signed-off-by: Alex-Brooks <[email protected]>

* Remove CLIP_API from func signature

Signed-off-by: Alex-Brooks <[email protected]>

* USE MAX_IMAGE_FEATURE_LAYERS const in layer calc

Signed-off-by: Alex-Brooks <[email protected]>

* Clarify feature layers are non negative ints and not uint

Signed-off-by: Alex-Brooks <[email protected]>

* Fix condition for reading feature layers

Signed-off-by: Alex-Brooks <[email protected]>

* pop last llava layer when feature layers are unset

Signed-off-by: Alex-Brooks <[email protected]>

* Fix unset vision layer 0

Signed-off-by: Alex-Brooks <[email protected]>

* Update examples/llava/clip.cpp

Co-authored-by: Xuan-Son Nguyen <[email protected]>

* Reenable assertion for out of bounds get_rows

Signed-off-by: Alex-Brooks <[email protected]>

* Use std vector for gridpoints and feature layers

Signed-off-by: Alex-Brooks <[email protected]>

* Caculate max feature layer at load time

Signed-off-by: Alex-Brooks <[email protected]>

* Include base patch for granite vision allocation

Signed-off-by: Alex-Brooks <[email protected]>

* Fix trailing whitespace

Signed-off-by: Alex-Brooks <[email protected]>

* Add max num patches = 10 back for minicpmv

Signed-off-by: Alex-Brooks <[email protected]>

* Use unordered set to store feature layers

Co-authored-by: Xuan-Son Nguyen <[email protected]>
Signed-off-by: Alex-Brooks <[email protected]>

* Use max feature layer for postnorm

Signed-off-by: Alex-Brooks <[email protected]>

* Apply suggestions from code review

---------

Signed-off-by: Alex-Brooks <[email protected]>
Co-authored-by: Xuan-Son Nguyen <[email protected]>