LLM-Inference/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-12 22:31:11 +04:00
Code Issues Packages Projects Releases Wiki Activity

vulkan: add TQ2_0 (ternary) support (#25850)

Browse Source 
* vulkan: TQ2_0 (ternary) support — dequant + dedicated mul_mat_vec + matmul via dequant_funcs

First Vulkan ternary type in ggml. Correctness: OM-125m TQ2_0 vs F16 top-12
logprobs identical to 4 decimals fully offloaded (float dequant path, no Q8_K
activation quant). Speed at 125m ~= F16 (overhead-bound at this scale); the
bandwidth win targets larger BitNet SKUs. MMQ/int-dot path intentionally not
wired yet.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* tests: enable TQ2_0 in backend-ops type lists

Vulkan now implements TQ2_0 (dequant, mul_mat_vec, mul_mm, get_rows); backends
without support skip via not-supported as usual. TQ1_0 stays disabled.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Michael Trabalka <michael.trabalka@sqv.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
michaeltrabalka-tech
2026-08-12 08:07:23 +03:00
committed by GitHub
co-authored by Michael Trabalka Claude Fable 5
parent 55f453b924
commit a7cd2f0e98
9 changed files with 257 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test-backend-ops.cpp
+4 -2
View File
@@ -8000,7 +8000,8 @@ static const ggml_type all_types[] = {
GGML_TYPE_Q2_K, GGML_TYPE_Q3_K,
GGML_TYPE_Q4_K, GGML_TYPE_Q5_K,
GGML_TYPE_Q6_K,
// GGML_TYPE_TQ1_0, GGML_TYPE_TQ2_0, // TODO: implement for all backends
GGML_TYPE_TQ2_0,
// GGML_TYPE_TQ1_0, // TODO: implement for all backends
GGML_TYPE_IQ2_XXS, GGML_TYPE_IQ2_XS, GGML_TYPE_IQ2_S,
GGML_TYPE_IQ3_XXS, GGML_TYPE_IQ1_S, GGML_TYPE_IQ1_M,
GGML_TYPE_IQ4_NL, GGML_TYPE_IQ3_S, GGML_TYPE_IQ4_XS,
@@ -8027,7 +8028,8 @@ static const ggml_type other_types[] = {
GGML_TYPE_Q2_K, GGML_TYPE_Q3_K,
GGML_TYPE_Q5_K,
GGML_TYPE_Q6_K,
// GGML_TYPE_TQ1_0, GGML_TYPE_TQ2_0, // TODO: implement for all backends
GGML_TYPE_TQ2_0,
// GGML_TYPE_TQ1_0, // TODO: implement for all backends
GGML_TYPE_IQ2_XS, GGML_TYPE_IQ2_S,
GGML_TYPE_IQ3_XXS, GGML_TYPE_IQ1_S, GGML_TYPE_IQ1_M,
GGML_TYPE_IQ4_NL, GGML_TYPE_IQ3_S, GGML_TYPE_IQ4_XS,