Skip to content

Releases: ggerganov/llama.cpp

b4458

10 Jan 06:22
c3f9d25
Compare
Choose a tag to compare
Vulkan: Fix float16 use on devices without float16 support + fix subg…

b4457

10 Jan 02:48
ee7136c
Compare
Choose a tag to compare
llama: add support for QRWKV6 model architecture (#11001)

llama: add support for QRWKV6 model architecture (#11001)

* WIP: Add support for RWKV6Qwen2

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

* RWKV: Some graph simplification

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

* Add support for RWKV6Qwen2 with cpu and cuda GLA

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

* RWKV6[QWEN2]: Concat lerp weights together to reduce cpu overhead

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

* Fix some typos

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

* code format changes

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

* Fix wkv test & add gla test

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

* Fix cuda warning

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

* Update README.md

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

* Update ggml/src/ggml-cuda/gla.cu

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

* Fix fused lerp weights loading with RWKV6

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

* better sanity check skipping for QRWKV6 in llama-quant

thanks @compilade

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

---------

Signed-off-by: Molly Sophia <[email protected]>
Co-authored-by: Georgi Gerganov <[email protected]>
Co-authored-by: compilade <[email protected]>

b4456

10 Jan 00:52
c6860cc
Compare
Choose a tag to compare
SYCL: Refactor ggml_sycl_compute_forward (#11121)

* SYCL: refactor ggml_sycl_compute_forward

* SYCL: add back GGML_USED(dst) to ggml_sycl_cpy

* SYCL: add function name to noop debug

* SYCL: Some device info print refactoring and add details of XMX availability

b4453

09 Jan 10:57
f8feb4b
Compare
Choose a tag to compare
model: Add support for PhiMoE arch (#11003)

* model: support phimoe

* python linter

* doc: minor

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

* doc: minor

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

* doc: add phimoe as supported model

ggml-ci

---------

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

b4451

09 Jan 09:51
d9feae1
Compare
Choose a tag to compare
llama-chat : add phi 4 template (#11148)

b4450

08 Jan 20:47
8d59d91
Compare
Choose a tag to compare
fix: add missing msg in static_assert (#11143)

Signed-off-by: hydai <[email protected]>

b4447

08 Jan 16:11
f7cd133
Compare
Choose a tag to compare
ci : use actions from ggml-org (#11140)

b4446

08 Jan 15:49
4d2b3d8
Compare
Choose a tag to compare
lora : improve compat with `mergekit-extract-lora` (#11131)

* (wip) support mergekit-extracted lora

* support mergekit-extract-lora

* use lora->get_scale

* correct comment

* correct norm name & condition

* add some hints

b4445

08 Jan 15:42
c07d437
Compare
Choose a tag to compare
llama : avoid hardcoded QK_K (#11061)

ggml-ci

b4443

08 Jan 12:24
c792dcf
Compare
Choose a tag to compare
ggml : allow loading backend with env variable (ggml/1059)

ref: #1058