Fix/hybrid cache reuse#17
Merged
visorcraft merged 4 commits intomasterfrom Mar 7, 2026
Merged
Conversation
For hybrid Mamba-Transformer models, the recurrent (SSM) cache cannot handle partial removal - this is inherent to how SSM state works (cumulative, not position-indexed like KV cache). Previously, when seq_rm failed for recurrent, the entire operation failed, causing the server to force n_past=0 (full prompt reprocessing). This change: 1. When recurrent seq_rm fails, clear recurrent state and mark for rebuild 2. Allow attention seq_rm to proceed (KV cache can handle partial removal) 3. Return success if attention succeeded 4. Change seq_pos_min to return attention pos_min (so server sees valid cache) The recurrent state rebuild tracking allows the model to know when SSM state needs to be recomputed from scratch during the next decode pass, while still benefiting from KV cache reuse for transformer layers. This significantly improves performance for hybrid models when: - Prompt is compacted (tokens decrease) - Context is trimmed - Any operation that would require partial cache removal Expected improvement: ~40-50% faster prefill after compaction for 50/50 hybrid models, since transformer layers can reuse cached KV while only Mamba layers need to recompute.
upstream
visorcraft
pushed a commit
that referenced
this pull request
Mar 12, 2026
…better shader parameter handling (ggml-org#20173) * K quant speedup (#20) * Basic JIT compilation for mul_mat, get_rows, and scale (#17) * scale jit working * preliminary working jit for getrows and mulmat, needs refining * simplified mul_mat preprocessing switch statement * get_rows fixes, mul_mat refinement * formatted + last edits * removed some extraneous prints * fixed get_rows, fixed workgroup dispatch in mul_mat. no gibberish * small fix * some changes, working * get_rows and mul_mat jit fixed and working * Update formatting * formatting * Add header --------- Co-authored-by: Neha Abbas <nehaabbas@ReeseLevines-MacBook-Pro.local> Co-authored-by: Reese Levine <reeselevine1@gmail.com> * Start work on all-encompassing shader library * refactor argmax, set_rows * Refactor all but flashattention, mat mul * no gibberish, all k quants added, merged * vec memory fix * q6_k matching metal on my machine, tests passing * Set tile size for q6_k separately * Separate out fast shaders --------- Co-authored-by: neha-ha <137219201+neha-ha@users.noreply.github.com> * Move towards writeBuffer for params * Move away from multiple buffers for set_rows errors, remove host buffer for parameter buffers, minor cleanups * Remove extra file * Formatting --------- Co-authored-by: neha-ha <137219201+neha-ha@users.noreply.github.com>
visorcraft
pushed a commit
that referenced
this pull request
Apr 25, 2026
) * ggml: backend-agnostic tensor parallelism * support for GPT-OSS, Qwen 3 MoE * partial Vulkan fix * add support for 4/8 GPUs * unconditional peer access * re-use buffers + ggml contexts * fix output pattern * NCCL support * GGML: HIP: add RCCL support * Remove shfl and AllReduce from backend interface * move allocation workaround out of ggml-alloc.c * 2d tensor set/get support * Fix the seg fault without NCCL * Apply suggestion from JohannesGaessler * support for tensor dims % n_devs != 0 * fix view_offs scaling * arbitrary num. of GPUs/tensor split * fix compilation * better granularity estimate * Support device-specific host buffer types if all underlying backends expose the same type. This allows using pinned memory instead of pageable memory for CUDA. Fix compilation errors. * partial Qwen 3 Next support * Fix qwen3 30b (#8) * Fix crash with Qwen-30B-A3B Q4_0 Qwen-30B-A3B Q4_0 has an intermediate dimension of 768. Using a granularity of 256 forces an uneven split between GPUs, which is not supported by the current implementation. * Decide block size based on tensor quantization type * Fix crashes due to KV cache serialization (#9) KV cache serialization requires non-zero offsets on the tensor. Add support in the meta backend to set/get a tensor with a non-zero offset. * metal : fix build (#7) * static memory allocations, fix usage count * fix tensor granularity * more even memory distribution * use BF16 for allreduce * rebase fixup * better error message for unsupported architectures * Fix device mismatch during scatter of allReduce. (#11) There is a mismatch between the dst buffer device and the backend device, causing the use of sync copies * Enable the previous allreduce implementation. It is better in both perf and stability (#12) * delay AllReduce for Moe for less I/O * build : clean-up compile warnings * backend : move most of the meta backend API to ggml-backend-impl.h * cont : hide unused public API in the implementation * llama : use llama_device + remove ggml_backend_dev_is_meta() * ggml-backend : remove unused alloc include * minor : remove regex include * ggml : introduce ggml-ext.h for staging new APIs * rebase fixup * fix tests * llama : more robust logic for determining Meta devices (#16) * llama : more robust logic for determining Meta devices * cont : fix devs size check Co-authored-by: Johannes Gäßler <johannesg@5d6.de> * cont : fix log type Co-authored-by: Johannes Gäßler <johannesg@5d6.de> --------- Co-authored-by: Johannes Gäßler <johannesg@5d6.de> * disable roundtrip for meta backend * fix arch selection * Qwen 3.5 support * fix Gemma 4 MoE * fix OpenVino, SYCL * fix test-llama-archs for CPU-only builds * Fix Qwen 3.5 MoE * disable meta backend tests for WebGPU * tests : filter CPU-based devices from the Meta backend tests (#17) * meta : formatting, naming, indentation (#18) * formatting : llama-model.cpp * formatting : ggml-ext.h * formatting : ggml-backend-meta.cpp * meta : add TODO * add documentation * better error messages * fix GPT-OSS --------- Co-authored-by: Carl Philipp Klemm <carl@uvos.xyz> Co-authored-by: Gaurav Garg <gaugarg@nvidia.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
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
1 participant
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.
Make sure to read the contributing guidelines before submitting a PR