marfrit/rk-llama.cpp
1
0
Fork 0
Code Issues Pull Requests Actions 28 Packages Projects Releases Wiki Activity

ggml-webgpu: FlashAttention refactor + standardize quantization support (#23834)

Browse Source 
* Start work on flash_attn refactor

* Refactor

* Split k/v quantization

* Refactor and abstract quantization logic for flash_attn and mul_mat

* Add quantization support to tile path

* formatting

* Move to functions, add a check
This commit is contained in:
Reese Levine
2026-06-03 22:05:04 -07:00
committed by GitHub
parent 3c7450cee1
commit e8c54893f2
11 changed files with 983 additions and 947 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test-backend-ops.cpp
+1
View File
@@ -9046,6 +9046,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_flash_attn_ext(64, 64, 4, {1, 1}, 128, 2, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_Q4_0, GGML_TYPE_F16));
test_cases.emplace_back(new test_flash_attn_ext(72, 72, 4, {1, 1}, 96, 2, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_Q4_0, GGML_TYPE_Q8_0));
test_cases.emplace_back(new test_flash_attn_ext(64, 64, 4, {1, 1}, 96, 2, true, false, 0, 0, GGML_PREC_F32, GGML_TYPE_F16, GGML_TYPE_F32));
test_cases.emplace_back(new test_flash_attn_ext(128, 128, 4, {1, 1}, 256, 1, false, false, 0, 0, GGML_PREC_F32, GGML_TYPE_F16, GGML_TYPE_Q4_0));
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_Q1_0, GGML_TYPE_Q1_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_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));