2bbe4c2cf8
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. |
||
|---|---|---|
| .. | ||
| peg-parser | ||
| .gitignore | ||
| CMakeLists.txt | ||
| get-model.cpp | ||
| get-model.h | ||
| run-json-schema-to-grammar.mjs | ||
| test-alloc.cpp | ||
| test-arg-parser.cpp | ||
| test-autorelease.cpp | ||
| test-backend-ops.cpp | ||
| test-backend-sampler.cpp | ||
| test-barrier.cpp | ||
| test-c.c | ||
| test-chat-parser.cpp | ||
| test-chat-peg-parser.cpp | ||
| test-chat-template.cpp | ||
| test-chat.cpp | ||
| test-double-float.cpp | ||
| test-gbnf-validator.cpp | ||
| test-gguf.cpp | ||
| test-grammar-integration.cpp | ||
| test-grammar-llguidance.cpp | ||
| test-grammar-parser.cpp | ||
| test-json-partial.cpp | ||
| test-json-schema-to-grammar.cpp | ||
| test-llama-grammar.cpp | ||
| test-log.cpp | ||
| test-lora-conversion-inference.sh | ||
| test-model-load-cancel.cpp | ||
| test-mtmd-c-api.c | ||
| test-opt.cpp | ||
| test-peg-parser.cpp | ||
| test-quantize-fns.cpp | ||
| test-quantize-perf.cpp | ||
| test-quantize-stats.cpp | ||
| test-regex-partial.cpp | ||
| test-rope.cpp | ||
| test-sampling.cpp | ||
| test-state-restore-fragmented.cpp | ||
| test-thread-safety.cpp | ||
| test-tokenizer-0.cpp | ||
| test-tokenizer-0.py | ||
| test-tokenizer-0.sh | ||
| test-tokenizer-1-bpe.cpp | ||
| test-tokenizer-1-spm.cpp | ||
| test-tokenizer-random.py | ||
| test-tokenizers-repo.sh | ||