vulkan: Use VK_EXT_shader_64bit_indexing to handle large mat_mul(_id)#18678
Merged
0cc4m merged 1 commit intoggml-org:masterfrom Jan 12, 2026
Merged
vulkan: Use VK_EXT_shader_64bit_indexing to handle large mat_mul(_id)#186780cc4m merged 1 commit intoggml-org:masterfrom
0cc4m merged 1 commit intoggml-org:masterfrom
Conversation
This fixes incoherent output in Llama-4-Maverick-17B-128E-PAB-Q8_0, which has a mul_mat_id with an A matrix that's Q8_0 8192 x 5120 x 128. This should work when the number of blocks in the A matrix is less than 2^32 (for mul_mat_vec or mul_mm_cm2), or for mul_mm I think the limit is like 2^32*LOAD_VEC_A elements. - Divide batch_stride by QUANT_K earlier, so the block index calculation works in 32b. - Each vk_pipeline_struct has a linked list of pipelines that will allow it to handle variants. So far this change just adds a single use case for this, compiling with the e64BitIndexingEXT flag. - Use the 64b indexing variant when the A matrix is larger than maxStorageBufferRange. 64-bit indexing has some cost - around 3-5% in MoE models, so it's worth the effort to avoid enabling it unconditionally.
github-actions
bot
added
testing
angt
pushed a commit
to angt/llama.cpp
that referenced
this pull request
Jan 12, 2026
…ggml-org#18678) This fixes incoherent output in Llama-4-Maverick-17B-128E-PAB-Q8_0, which has a mul_mat_id with an A matrix that's Q8_0 8192 x 5120 x 128. This should work when the number of blocks in the A matrix is less than 2^32 (for mul_mat_vec or mul_mm_cm2), or for mul_mm I think the limit is like 2^32*LOAD_VEC_A elements. - Divide batch_stride by QUANT_K earlier, so the block index calculation works in 32b. - Each vk_pipeline_struct has a linked list of pipelines that will allow it to handle variants. So far this change just adds a single use case for this, compiling with the e64BitIndexingEXT flag. - Use the 64b indexing variant when the A matrix is larger than maxStorageBufferRange. 64-bit indexing has some cost - around 3-5% in MoE models, so it's worth the effort to avoid enabling it unconditionally.
gary149
pushed a commit
to gary149/llama-agent
that referenced
this pull request
Jan 13, 2026
…ggml-org#18678) This fixes incoherent output in Llama-4-Maverick-17B-128E-PAB-Q8_0, which has a mul_mat_id with an A matrix that's Q8_0 8192 x 5120 x 128. This should work when the number of blocks in the A matrix is less than 2^32 (for mul_mat_vec or mul_mm_cm2), or for mul_mm I think the limit is like 2^32*LOAD_VEC_A elements. - Divide batch_stride by QUANT_K earlier, so the block index calculation works in 32b. - Each vk_pipeline_struct has a linked list of pipelines that will allow it to handle variants. So far this change just adds a single use case for this, compiling with the e64BitIndexingEXT flag. - Use the 64b indexing variant when the A matrix is larger than maxStorageBufferRange. 64-bit indexing has some cost - around 3-5% in MoE models, so it's worth the effort to avoid enabling it unconditionally.
dillon-blake
pushed a commit
to Boxed-Logic/llama.cpp
that referenced
this pull request
Jan 15, 2026
…ggml-org#18678) This fixes incoherent output in Llama-4-Maverick-17B-128E-PAB-Q8_0, which has a mul_mat_id with an A matrix that's Q8_0 8192 x 5120 x 128. This should work when the number of blocks in the A matrix is less than 2^32 (for mul_mat_vec or mul_mm_cm2), or for mul_mm I think the limit is like 2^32*LOAD_VEC_A elements. - Divide batch_stride by QUANT_K earlier, so the block index calculation works in 32b. - Each vk_pipeline_struct has a linked list of pipelines that will allow it to handle variants. So far this change just adds a single use case for this, compiling with the e64BitIndexingEXT flag. - Use the 64b indexing variant when the A matrix is larger than maxStorageBufferRange. 64-bit indexing has some cost - around 3-5% in MoE models, so it's worth the effort to avoid enabling it unconditionally.
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
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.
This fixes incoherent output in Llama-4-Maverick-17B-128E-PAB-Q8_0, which has a mul_mat_id with an A matrix that's Q8_0 8192 x 5120 x 128.
This should work when the number of blocks in the A matrix is less than 2^32 (for mul_mat_vec or mul_mm_cm2), or for mul_mm I think the limit is like 2^32*LOAD_VEC_A elements.
64-bit indexing has some cost - around 3-5% in MoE models, so it's worth the effort to avoid enabling it unconditionally.