ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

vulkan: implement initial support for IQ2 and IQ3 quantizations (#11360)

Browse source 
* vulkan: initial support for IQ3_S

* vulkan: initial support for IQ3_XXS

* vulkan: initial support for IQ2_XXS

* vulkan: initial support for IQ2_XS

* vulkan: optimize Q3_K by removing branches

* vulkan: implement dequantize variants for coopmat2

* vulkan: initial support for IQ2_S

* vulkan: vertically realign code

* port failing dequant callbacks from mul_mm

* Fix array length mismatches

* vulkan: avoid using workgroup size before it is referenced

* tests: increase timeout for Vulkan llvmpipe backend

---------

Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
This commit is contained in:
Rémy Oudompheng 2025-01-29 18:29:39 +01:00 • committed by GitHub
parent e51c47b401
commit 66ee4f297c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 1616 additions and 40 deletions
Download patch file Download diff file Expand all files Collapse all files

4
ggml/src/ggml-vulkan/vulkan-shaders/get_rows_quant.comp
View file

@ -12,8 +12,8 @@ void main() {
const uint i11 = (gl_GlobalInvocationID.z)/p.ne12;
const uint i12 = (gl_GlobalInvocationID.z)%p.ne12;
#if defined(DATA_A_IQ4_NL)
init_iq4nl_shmem();
#if defined(DATA_A_IQ2_XXS) || defined(DATA_A_IQ2_XS) || defined(DATA_A_IQ2_S) || defined(DATA_A_IQ3_XXS) || defined(DATA_A_IQ3_S) || defined(DATA_A_IQ4_NL)
init_iq_shmem(gl_WorkGroupSize);
#endif
if (i00 >= p.ne00) {