ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-18 23:08:08 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

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

Browse Source 
llama: add support for QRWKV6 model architecture (llama/11001)

* WIP: Add support for RWKV6Qwen2

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* RWKV: Some graph simplification

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Add support for RWKV6Qwen2 with cpu and cuda GLA

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

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

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Fix some typos

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* code format changes

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Fix wkv test & add gla test

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Fix cuda warning

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Update README.md

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

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

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Fix fused lerp weights loading with RWKV6

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* better sanity check skipping for QRWKV6 in llama-quant

thanks @compilade

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
Co-authored-by: compilade <git@compilade.net>

---------

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: compilade <git@compilade.net>
This commit is contained in:
Molly Sophia
2025-01-10 09:58:08 +08:00
committed by Georgi Gerganov
parent c3235bd81e
commit 06209f6683
9 changed files with 367 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-vulkan/ggml-vulkan.cpp
View File

@ -5633,9 +5633,9 @@ static void ggml_vk_op_f32_rwkv6(ggml_backend_vk_context * ctx, vk_context& subc
}
static void ggml_vk_rwkv_wkv6(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst, bool dryrun = false) {
const size_t seq_length = dst->src[0]->ne[3];
const size_t seq_length = dst->src[0]->ne[2];
const size_t n_embed = dst->ne[0];
const size_t n_heads = dst->src[0]->ne[2];
const size_t n_heads = dst->src[0]->ne[1];
const size_t n_seqs = dst->src[5]->ne[1];
ggml_vk_op_f32_rwkv6(