Minor set_rows optimization #4
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
reeselevine
reviewed
Oct 8, 2025
| webgpu_pipeline memset_pipeline; | ||
| webgpu_pipeline mul_mat_pipeline[30][2]; | ||
| webgpu_pipeline set_rows_pipeline; | ||
| webgpu_pipeline set_rows_f32_no_vec_pipeline; |
There was a problem hiding this comment.
can you combine this with the above pipeline, and just call it set_rows_pipeline? Then you can index into it like set_rows_pipeline[dst->type][vectorized]. (Also, this is really an f16 pipeline, since the src is always f32 I believe.
| static void ggml_webgpu_init_set_rows_pipeline(webgpu_context & webgpu_ctx) { | ||
| ggml_webgpu_create_pipeline(webgpu_ctx->device, webgpu_ctx->set_rows_pipeline, wgsl_set_rows, "set_rows", | ||
| // create_pipeline(device, pipeline, shader_code, label, constants) | ||
| ggml_webgpu_create_pipeline(webgpu_ctx->device, webgpu_ctx->set_rows_f32_no_vec_pipeline, wgsl_set_rows_f32, "set_rows_f32", |
There was a problem hiding this comment.
make sure you run clang-format on this.
| }; | ||
|
|
||
| size_t max_wg_size = ctx->max_wg_size_x; | ||
| uint32_t wg_x = (src->ne[1] * src->ne[2] * src->ne[3] + max_wg_size - 1) / max_wg_size; |
There was a problem hiding this comment.
since the type has changed, the number of threads will also need to change for efficiency
| return ggml_backend_webgpu_build(ctx, ctx->set_rows_pipeline, params, entries, wg_x, error_bufs); | ||
| webgpu_pipeline pipeline = ctx->set_rows_pipeline; | ||
| // if not evenly divisble by 4, use the non-vectorized version | ||
| if (src->type == GGML_TYPE_F32 && dst->ne[0] % 4 != 0) { |
There was a problem hiding this comment.
src and dst will have the same number of columns, and src->type will always be f32. So perhaps we should just check src->ne[0]
SharmaRithik
pushed a commit
to SharmaRithik/local-llama.cpp
that referenced
this pull request
Oct 10, 2025
…gml-org#16038) Initalizing RESERVED_NAME in is_reserved_name() is not thread safe and leads to corrupted memory when used from multiple threads as can be seen in the asan trace below. This fixes the initialization to make it thread-safe. #0 0x000100abd018 in std::__1::pair<std::__1::__hash_iterator<std::__1::__hash_node<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, void*>*>, bool> std::__1::__hash_table<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, std::__1::hash<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>, std::__1::equal_to<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>, std::__1::allocator<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>>::__emplace_unique_key_args<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&>(std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&) __hash_table:1565 reeselevine#1 0x000100ab0320 in SchemaConverter::visit(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&) json-schema-to-grammar.cpp:802 reeselevine#2 0x000100aafc48 in std::__1::__function::__func<build_grammar(std::__1::function<void (common_grammar_builder const&)> const&, common_grammar_options const&)::$_2, std::__1::allocator<build_grammar(std::__1::function<void (common_grammar_builder const&)> const&, common_grammar_options const&)::$_2>, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> (std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&, nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&)>::operator()(std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&, nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&) function.h:319 reeselevine#3 0x000100a2c938 in std::__1::__function::__func<common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool)::$_0::operator()(common_grammar_builder const&) const::'lambda'(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&), std::__1::allocator<common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool)::$_0::operator()(common_grammar_builder const&) const::'lambda'(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&)>, void (nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&)>::operator()(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&) function.h:319 reeselevine#4 0x000100a139f8 in foreach_function(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&, std::__1::function<void (nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&)> const&) chat.cpp:762 reeselevine#5 0x000100a2a7f4 in std::__1::__function::__func<common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool)::$_0, std::__1::allocator<common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool)::$_0>, void (common_grammar_builder const&)>::operator()(common_grammar_builder const&) function.h:319 reeselevine#6 0x000100aa98f4 in build_grammar(std::__1::function<void (common_grammar_builder const&)> const&, common_grammar_options const&) json-schema-to-grammar.cpp:982 reeselevine#7 0x0001009c9314 in common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool) chat.cpp:1110 ggml-org#8 0x0001009b8afc in common_chat_templates_apply_jinja(common_chat_templates const*, common_chat_templates_inputs const&) chat.cpp:1992 ggml-org#9 0x0001009b533c in common_chat_templates_apply(common_chat_templates const*, common_chat_templates_inputs const&) chat.cpp:2074 ggml-org#10 0x000100810120 in llamacpp_apply_chat_template+0x724 (predict_oai-98384e17fb94e863:arm64+0x100090120) ... ==45482==Register values: x[0] = 0x00006020004147f8 x[1] = 0x00006080000013c8 x[2] = 0x0000000000000000 x[3] = 0x0000604006289738 x[4] = 0x0000000000000002 x[5] = 0x0000000000000001 x[6] = 0x04034000004b4000 x[7] = 0x0000000000000001 x[8] = 0xbebebebebebebebe x[9] = 0x17d7d7d7d7d7d7d7 x[10] = 0x00000c04000828ff x[11] = 0x0000000000000001 x[12] = 0x000000002018d383 x[13] = 0x0000000000000000 x[14] = 0xfa0000000000fafa x[15] = 0x000010700001ffff x[16] = 0x000000019dc012c0 x[17] = 0x00000001021284f8 x[18] = 0x0000000000000000 x[19] = 0x00000001700acdc0 x[20] = 0x0000000000000002 x[21] = 0x000000002018d384 x[22] = 0x16dd16fd2e731151 x[23] = 0x0000007000020000 x[24] = 0x0000000100c69c08 x[25] = 0x0000000100c69c20 x[26] = 0x00006080000013c7 x[27] = 0x0000000100c69c00 x[28] = 0x00000001700acd60 fp = 0x00000001700aceb0 lr = 0x0000000100abce30 sp = 0x00000001700acd60 AddressSanitizer can not provide additional info. SUMMARY: AddressSanitizer: SEGV __hash_table:1565 in std::__1::pair<std::__1::__hash_iterator<std::__1::__hash_node<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, void*>*>, bool> std::__1::__hash_table<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, std::__1::hash<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>, std::__1::equal_to<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>, std::__1::allocator<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>>::__emplace_unique_key_args<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&>(std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&) Thread T5 created by T0 here: #0 0x0001020b99d4 in pthread_create+0x5c (libclang_rt.asan_osx_dynamic.dylib:arm64e+0x359d4) reeselevine#1 0x000100873910 in std::sys::pal::unix::thread::Thread::new::h77254fdd87a28e05+0x118 (predict_oai-98384e17fb94e863:arm64+0x1000f3910) reeselevine#2 0x0001007c7a1c in test::run_test::haeb3c2bcd5ed6cf6+0x76c (predict_oai-98384e17fb94e863:arm64+0x100047a1c) reeselevine#3 0x0001007aedb0 in test::console::run_tests_console::he9d142d704f3a986+0x149c (predict_oai-98384e17fb94e863:arm64+0x10002edb0) reeselevine#4 0x0001007c5758 in test::test_main::hf86a5e20735245b9+0x118 (predict_oai-98384e17fb94e863:arm64+0x100045758) reeselevine#5 0x0001007c5da0 in test::test_main_static::h61ee9c8fd30abca0+0x54 (predict_oai-98384e17fb94e863:arm64+0x100045da0) ... ==45482==ABORTING
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
If the source array is divisible evenly by 4, each thread will copy over 4 values at once to the destination array.