Rebase #4
Open
Rebase #4
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
* vulkan: Handle updated FA dim2/3 definition Pack mask boolean and n_head_log2 into a single dword to keep the push constant block under the 128B limit. * handle null mask for gqa * allow gqa with dim3>1
The fused operation was grabbing the epsilon value from the wrong place. Add an env var to disable fusion. Add some missing checks for supported shapes/types. Handle fused rms_norm+mul in check_results.
Commit taken from remyoudompheng's PR #12260 Co-authored-by: Rémy Oudompheng <[email protected]>
Signed-off-by: Xiaodong Ye <[email protected]>
* cuda : fix rope non-cont ggml-ci * cont : fix multi-rope + add test ggml-ci * sycl : try fix ggml-ci * cont : fix sycl + clean-up cuda ggml-ci
* model : add hunyuan moe * tokenizer ok * fix tensor name * cgraph init * chat template * wip * almost working * skip embed, fix bos * cleanup * yarn scaling * cleanup * correct rope type * failed token fix * ntk alpha freq_base * tokenization working * cleanup and pr changes * vocab_size sanity check * ntk alpha generic * Update convert_hf_to_gguf.py * Apply suggestions from code review * fix regression * fix style --------- Co-authored-by: kooshi <[email protected]>
* Add server_prefix * Correct server path env * Rename cli flag to --api-prefix * Change all to api_prefix
Splits producing more than one ubatch per batch for recurrent models were broken with #14512. This fixes it by moving the completeness check after the ubatch split loop.
* Init - first pass. * Model -> ModelBase. * fix errors in conversion. * Update the graph. * up. * up. * wip * cgraph ok * rm redundant code --------- Co-authored-by: Vaibhavs10 <[email protected]>
Signed-off-by: stevenkuang <[email protected]>
* vulkan: allow FA split_k with smaller KV values * vulkan: spread split_k_reduce work across more threads k_num can get rather large. Use the whole workgroup to reduce the M/L values. Launch a thread for each element in the HSV dimension of the output. Helps a lot for large HSV (like deepseek).
* v1 * push more fixes * another fix * fix * more fixes * minor fix * more cleaning on python code * python fixes * changed precision for multipliers float 32->64 * fixes * another fix * fix * pre-norm -> norm * fix * Revert "fix" This reverts commit 243e4d1. * fix * small fix ffn_norm * try * mix instead of max * fix vocab size * conflict solve * fixed multipliers * falcon-h1 specefic vocab resolved * read arch from gguf.MODEL_ARCH * mamba_d_ssm added to d_inner find_hparam * remove unused functions from gguf_writer.py * override modify_tensors instead of get_tensors * fix conversion and d_inner * added some cb functions for debugging puposes * inp_out_ids moved outside of layers loop * mup_vec create as float64 * fix rope_theta * injected mup * clean ups * rm extra space * rm unused MAMBA_CHUNK_SIZE * rm unused key * add bos False * changed ROPE_TYPE * cleaning debugging stuff * cleaning debug quant * fix comment * some cleanups * some cleanups * Update src/llama-model-loader.cpp * more cleanups * moe cleanuips * d_ssm -> d_inner; * cleaning unused hparams * cleanup * more cleanups * more cleanups on python conversion; * minor cleanups * Apply suggestions from code review Co-authored-by: Georgi Gerganov <[email protected]> * remove todo * added falcon-h1 * tensor not required * clean * remove unneeded attributes * more cleanups and fixed conversion * remove final_norm * flake8 fixes * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <[email protected]> * flake8 fixes * Update src/llama-hparams.cpp Co-authored-by: Sigbjørn Skjæret <[email protected]> * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <[email protected]> * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <[email protected]> * Update src/llama-arch.cpp Co-authored-by: Sigbjørn Skjæret <[email protected]> * Update convert_hf_to_gguf.py Co-authored-by: Sigbjørn Skjæret <[email protected]> * added hashes * Update src/llama-arch.cpp Co-authored-by: Georgi Gerganov <[email protected]> * Update src/llama-vocab.cpp Co-authored-by: Georgi Gerganov <[email protected]> * update the update file * Revert "update the update file" This reverts commit 082ab4a. * fix: address suggestions * fix: update convert_hf_to_gguf.py * Update gguf-py/gguf/constants.py Co-authored-by: Sigbjørn Skjæret <[email protected]> * Update src/llama-model-loader.cpp Co-authored-by: Sigbjørn Skjæret <[email protected]> * d_inner fixed * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <[email protected]> * reshaping ssm_norm for 34B * removing generate_mup * remove duplicates metadata keys * rm comment * final comment * fix unused args * fix constants * fix bad merge * Update src/llama-model.cpp Co-authored-by: compilade <[email protected]> * falcon-h1: remove unused ssm_in_b and bad merge * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <[email protected]> * falcon-h1: fix last comment * Update convert_hf_to_gguf.py Co-authored-by: compilade <[email protected]> * falcon-h1: revert add_add_bos(False) * falcon-h1: fix tied weights * falcon-h1: remove whitespace * falcon-h1: fix wrong size param * falcon-h1: fix whitespace issues --------- Co-authored-by: younesbelkada <[email protected]> Co-authored-by: Younes B <[email protected]> Co-authored-by: Georgi Gerganov <[email protected]> Co-authored-by: Sigbjørn Skjæret <[email protected]> Co-authored-by: compilade <[email protected]>
* ggml : add ggml_scale_bias * ggml_vec_mad1_f32 * add more simd * add CUDA * sycl * vulkan * cann (placeholder) * opencl * will this fix cpu? * fix cuda * suggestions from coderabbit * fix cann compile error * vDSP_vsmsa * rm __ARM_FEATURE_SVE * use memcpy for op params * make code looks more consistent * use scalar for __ARM_FEATURE_SVE * add x param to ggml_vec_mad1_f32
* wip: llama : separate recurrent states from the KV cache This will be necessary to support Jamba (and other recurrent models mixed with Attention). Doesn't compile yet, and finding a slot isn't yet done correctly for recurrent states. * llama : use std::find for seq_nodes in llama_rs_cache * llama : state checkpoints for recurrent models * llama : correctly handle more edge cases for the rs cache * llama : rename many llama_kv_cache_* functions * llama : remove useless return value for some llama_cache_* functions * llama : rethink recurrent state cell counts * llama : begin work on support for variable GQA This will also be useful for Jamba if we consider the Mamba layers to have 0 KV heads. * llama : gracefully fail when not finding hybrid slot * llama : support Jamba * llama : fix BERT inference without KV cache * convert-hf : check for unprocessed Jamba experts * convert-hf : support Mini-Jamba conversion * llama : fix Jamba quantization sanity checks * llama : sequence-length-aware batch splitting * llama : use equal-sequence-length sub-batches for recurrent models * ggml : simplify SSM-related operators * llama : make recurrent state slot allocation contiguous * llama : adapt internal uses of batches to llama_ubatch * llama : fix batch split output count for embeddings * llama : minimize swaps when reordering logits This reduces overhead when running hellaswag on thousands of sequences with very small 100k params Mamba models. * llama : fix edge case finding batch seq_id of split recurrent cell This otherwise was a problem when running the HellaSwag benchmark with small batch sizes, making it crash. * llama : avoid copies for simple batch splits * ggml : make ggml_ssm_scan not modify its source tensors * llama : fix shared recurrent tail cell count for small ubatch sizes Otherwise it was impossible to run the 'parallel' example with '-ub 1' with a Mamba or Jamba model. * llama : fix .base() compilation error on Windows * llama : allow doing the equivalent of SSM_CONV with SUM_ROWS and MUL * ggml : allow GGML_OP_CONCAT to work on non-contiguous tensors The implementation already supported it, and this makes Mamba's conv step slightly faster. * mamba : fix non-contiguous usage of ggml_silu * llama : session saving and reloading for hybrid models * convert_hf : fix Jamba conversion * llama : fix mixed signedness comparison * llama : use unused n_embd_k_gqa in k_shift This also slightly reduces the diff from the master branch * llama : begin renaming llama_past back to llama_kv_cache * llama : remove implicit recurrent state rollbacks * llama : partially apply clang-format style * convert : fix jamba conv1d shape squeezing * graph : add back hybrid memory graph input But this time it contains the sub-cache graph inputs. This *should* make it easier to handle updating the inputs when caching the graph (eventually). * model : add Jamba to Mamba-specific hparams printing * jamba : remove redundant nullptr initializations * model : remove unnecessary prefix for tensor loading constants Co-authored-by: Sigbjørn Skjæret <[email protected]> * model : use ggml_swiglu_split for Mamba Co-authored-by: Sigbjørn Skjæret <[email protected]> * model : make falcon-h1 use shared mamba2 layer builder * memory : avoid referring to KV in recurrent cache logs * gguf-py : avoid adding duplicate tensor mappings for Jamba Some of the tensor names are common with Llama4 --------- Co-authored-by: Sigbjørn Skjæret <[email protected]>
…4392) * compare-commits.sh: support both llama-bench and test-backend-ops Signed-off-by: Xiaodong Ye <[email protected]> * Speed up the build by specifying -j 12 Signed-off-by: Xiaodong Ye <[email protected]> * Remove build_number from test-backend-ops db Signed-off-by: Xiaodong Ye <[email protected]> * Apply suggestion from @JohannesGaessler Co-authored-by: Johannes Gäßler <[email protected]> * Refine tool selection logic Signed-off-by: Xiaodong Ye <[email protected]> * Address review comments Signed-off-by: Xiaodong Ye <[email protected]> --------- Signed-off-by: Xiaodong Ye <[email protected]> Signed-off-by: Xiaodong Ye <[email protected]> Co-authored-by: Johannes Gäßler <[email protected]>
* docker: add cann build pipline * docker: add cann build pipline * docker: fix cann devops * cann : fix multi card hccl * Update ggml/src/ggml-cann/ggml-cann.cpp Co-authored-by: Xuan-Son Nguyen <[email protected]> * Update ggml-cann.cpp --------- Co-authored-by: Georgi Gerganov <[email protected]> Co-authored-by: Xuan-Son Nguyen <[email protected]>
* Initial Q2_K Block Interleaving Implementation * Addressed review comments and clean up of the code * Post rebase fixes * Initial CI/CD fixes * Update declarations in arch-fallback.h * Changes for GEMV Q2_K in arch-fallback.h * Enable repacking only on AVX-512 machines * Update comments in repack.cpp * Address q2k comments --------- Co-authored-by: Manogna-Sree <[email protected]>
* support hunyuan_v1_dense Signed-off-by: stevenkuang <[email protected]> * update hunyuan_moe to hunyuan_v1_moe Signed-off-by: stevenkuang <[email protected]> * fix rope alpha assert and bos token Signed-off-by: stevenkuang <[email protected]> * add blank line Signed-off-by: stevenkuang <[email protected]> * Revert "update hunyuan_moe to hunyuan_v1_moe" This reverts commit aa973ca. * use hunyuan_dense instead of hunyuan_v1_dense Signed-off-by: stevenkuang <[email protected]> * fix hunyuan_moe chat template Signed-off-by: stevenkuang <[email protected]> * remove leftover code Signed-off-by: stevenkuang <[email protected]> * update hunyuan dense chat template Signed-off-by: stevenkuang <[email protected]> * fix hunyuan dense vocab and chat template Signed-off-by: stevenkuang <[email protected]> --------- Signed-off-by: stevenkuang <[email protected]>
* vendor : update vendored copy of google/minja Signed-off-by: Lennart Austenfeld <[email protected]> * Re-remove trailing whitespace Signed-off-by: Lennart Austenfeld <[email protected]> * Remove another trailing whitespace Signed-off-by: Lennart Austenfeld <[email protected]> --------- Signed-off-by: Lennart Austenfeld <[email protected]>
* vulkan: optimizations for direct convolution - Empirically choose a better tile size. Reducing BS_K/BS_NPQ helps fill the GPU. The new size should be amenable to using coopmat, too. - Fix shmem bank conflicts. 16B padding should work with coopmat. - Some explicit loop unrolling. - Skip math/stores work for parts of the tile that are OOB. - Apply fastdiv opt. - Disable shuffles for NV. * Three tiles sizes for CONV_2D, and a heuristic to choose * reallow collectives for pre-Turing * make SHMEM_PAD a spec constant * fixes for intel perf - no shmem padding, placeholder shader core count * shader variants with/without unrolling * 0cc4m's fixes for AMD perf Co-authored-by: 0cc4m <[email protected]> --------- Co-authored-by: 0cc4m <[email protected]>
Signed-off-by: Xiaodong Ye <[email protected]>
- Increase tile size for k-quants, to match non-k-quants - Choose more carefully between large and medium tiles, considering how it interacts with split_k - Allow larger/non-power of two split_k, and make the splits a multiple of 256 - Use split_k==3 to when >1/2 and <=2/3 of the SMs would hae been used
* torch is not required for convert_hf_to_gguf_update * add --check-missing parameter * check that pre-tokenizer hashes are up-to-date
* cuda, sycl : fix batched gemm when ne02 == 1 && ne03 > 1 ggml-ci * cont : fix cont types ggml-ci * cont : adopt variable names and comment from the other branch
…5040) This commit removes the right alignment the `n_stream` value in the log message in the `llama_kv_cache_unified` constructor. The motivation for this change is to enhance the readability of log message. Currently the output looks like this: ```console llama_kv_cache_unified: size = 2048.00 MiB ( 4096 cells, 32 layers, 1/ 1 seqs), K (f16): 1024.00 MiB, V (f16): 1024.00 MiB ``` Notice that the `n_stream` value is right aligned, which makes it a little harder to read. With the change in this commit the output will look like ```console llama_kv_cache_unified: size = 2048.00 MiB ( 4096 cells, 32 layers, 1/1 seqs), K (f16): 1024.00 MiB, V (f16): 1024.00 MiB ```
… text_config) (#15051) * basic kimi-vl textmodel conversion * check config["text_config"] for special tokens
…14994) * imatrix : use a single count for dense 3d tensors * imatrix : fix 3d activations when model tensor is 2d * imatrix : fix 3d tensor counts
* imatrix : use GGUF by default * imatrix : use GGUF regardless of the output filename The legacy format can only be produced with --output-format dat
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
No description provided.