Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

CUDA: add Q2_0 support (#25707)

Browse Source
This commit is contained in:
Pasha Khosravi
2026-07-30 12:33:25 +03:00
committed by GitHub
parent b2f221684f
commit 9b2a088819
20 changed files with 326 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test-backend-ops.cpp
+5
View File
@@ -8013,6 +8013,7 @@ static const ggml_type other_types[] = {
GGML_TYPE_Q5_0, GGML_TYPE_Q5_1,
GGML_TYPE_Q8_0,
GGML_TYPE_Q1_0,
GGML_TYPE_Q2_0,
GGML_TYPE_Q2_K, GGML_TYPE_Q3_K,
GGML_TYPE_Q5_K,
GGML_TYPE_Q6_K,
@@ -9563,6 +9564,10 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_flash_attn_ext(128, 64, 4, {1, 1}, 128, 2, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_Q1_0, GGML_TYPE_Q4_0));
test_cases.emplace_back(new test_flash_attn_ext(64, 128, 4, {1, 1}, 128, 2, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_Q4_0, GGML_TYPE_Q1_0));
test_cases.emplace_back(new test_flash_attn_ext(128, 64, 4, {1, 1}, 64, 2, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_Q1_0, GGML_TYPE_F16));
test_cases.emplace_back(new test_flash_attn_ext(128, 128, 4, {1, 1}, 96, 2, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_Q2_0, GGML_TYPE_Q2_0));
test_cases.emplace_back(new test_flash_attn_ext(128, 64, 4, {1, 1}, 128, 2, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_Q2_0, GGML_TYPE_Q4_0));
test_cases.emplace_back(new test_flash_attn_ext(64, 128, 4, {1, 1}, 128, 2, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_Q4_0, GGML_TYPE_Q2_0));
test_cases.emplace_back(new test_flash_attn_ext(128, 64, 4, {1, 1}, 64, 2, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_Q2_0, GGML_TYPE_F16));
// large-KV F16 cases (Qwen3.6-27B geometry and a llama-class control): the upstream matrix
// stops at kv=1024, blind to long-context FA bugs (e.g. the oneDNN SDPA ordering race on BMG).