Reshape the commits on top of b6298
#12
Closed
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
* support hunyuan_v1_dense Signed-off-by: stevenkuang <stevenkuang@tencent.com> * update hunyuan_moe to hunyuan_v1_moe Signed-off-by: stevenkuang <stevenkuang@tencent.com> * fix rope alpha assert and bos token Signed-off-by: stevenkuang <stevenkuang@tencent.com> * add blank line Signed-off-by: stevenkuang <stevenkuang@tencent.com> * Revert "update hunyuan_moe to hunyuan_v1_moe" This reverts commit aa973ca21913aba77f6e81a935270ef7be222e75. * use hunyuan_dense instead of hunyuan_v1_dense Signed-off-by: stevenkuang <stevenkuang@tencent.com> * fix hunyuan_moe chat template Signed-off-by: stevenkuang <stevenkuang@tencent.com> * remove leftover code Signed-off-by: stevenkuang <stevenkuang@tencent.com> * update hunyuan dense chat template Signed-off-by: stevenkuang <stevenkuang@tencent.com> * fix hunyuan dense vocab and chat template Signed-off-by: stevenkuang <stevenkuang@tencent.com> --------- Signed-off-by: stevenkuang <stevenkuang@tencent.com>
* vendor : update vendored copy of google/minja Signed-off-by: Lennart Austenfeld <l.austenfeld@googlemail.com> * Re-remove trailing whitespace Signed-off-by: Lennart Austenfeld <l.austenfeld@googlemail.com> * Remove another trailing whitespace Signed-off-by: Lennart Austenfeld <l.austenfeld@googlemail.com> --------- Signed-off-by: Lennart Austenfeld <l.austenfeld@googlemail.com>
* 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 <picard12@live.de> --------- Co-authored-by: 0cc4m <picard12@live.de>
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
- 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
* Add parameter buffer pool, batching of submissions, refactor command building/submission * Add header for linux builds * Free staged parameter buffers at once * Format with clang-format * Fix thread-safe implementation * Use device implicit synchronization * Update workflow to use custom release * Remove testing branch workflow
* model: Add GLM 4.5 (#14921) Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Merge in PR suggestions Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * model: Add GLM 4.5 family of models (#14921) 1. Updated tensor_mapping.py with NextN tensor mappings - Added proper tensor mappings for all NextN/MTP tensors in /Users/samm/git/llama.cpp/gguf-py/gguf/tensor_mapping.py - Added mappings for: eh_proj, embed_tokens, enorm, hnorm, shared_head.head, shared_head.norm 2. Added num_nextn_predict_layers configuration - Added LLM_KV_NUM_NEXTN_PREDICT_LAYERS constant to llama-arch.h and llama-arch.cpp - Added num_nextn_predict_layers field to llama_hparams struct - Updated GLM4_MOE parameter loading in llama-model.cpp to read this parameter - Modified tensor loading logic to conditionally load NextN tensors based on num_nextn_predict_layers - Added GGUF writer support in gguf_writer.py with add_num_nextn_predict_layers() method - Updated conversion script to extract and write this parameter from HuggingFace config 3. Added FIM tokens for GLM4_MOE - Added GLM-4.5's FIM tokens to llama-vocab.cpp: - <|code_prefix|> for FIM_PRE - <|code_suffix|> for FIM_SUF - <|code_middle|> for FIM_MID 4. Removed manual NextN tensor handling - Removed the special-case handling in convert_hf_to_gguf.py that manually mapped NextN tensors - NextN tensors are now handled automatically through the proper tensor mapping system * glm 4.5 update tensors names * model: glm 4.5 apply suggestions from code review Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * model: glm 4.5 apply suggestions from code review Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * model: glm 4.5 apply suggestions from code review * Apply suggestions from code review * patch broken chat template * typings fix * add TENSOR_SKIP flag Co-authored-by: Diego Devesa <slarengh@gmail.com> * Update src/llama-model-loader.h Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> Co-authored-by: Diego Devesa <slarengh@gmail.com>
* convert : fix tensor naming conflict for llama 4 vision * convert ok * support kimi vision model * clean up * fix style * fix calc number of output tokens * refactor resize_position_embeddings * add test case * rename build fn * correct a small bug
* metal : optmize FA vec for large heads and sequences * metal : adjust small-batch mul mv kernels ggml-ci * batched-bench : fix total speed computation ggml-ci * cont : add comments ggml-ci
This commit adds two targets to the Makefile for quantizing of Quantization Aware Trained (QAT) models to Q4_0 format. The motivation for this is that this sets the token embedding and the output tensors data types to Q8_0 instead of the default Q6_K. This is someting that we wish to enforce for QAT Q4_0 models that are to be uploaded to ggml-org on Huggingface to guarantee the best quality.
This patch improves GEMM for FP32 Data Type on PowerPC Implements GEMM on large blocks with configurable block size mc, nc, kc (default: 256, 256, 256). Packing Function optimized to access blocks as per memory layout. GEMM Optimized to work on larger blocks. Isolated Packing from GEMM Operations for better MMA utilization. Verified functionality and correctness uing llama-cli and stand alone test case (performs matmul and compares final mattrix C result with base). Minor code refactoring changes: Replace macro with inline function Code Indent made consistent with 4 spaces Performance Testing: Observed 50% ~ 70% improvement in Prompt Processing Speed mesured using llama-bench with Meta-Llama3-8B FP32 Model. Similar gains observed with Mistral-7b-Instruct-v0.3 Model. model Size Params Backend Threads Test Patch Base llama 8B all F32 29.92 GiB 8.03 B CPU 20 pp512 98.58 60.3 llama 8B all F32 29.92 GiB 8.03 B CPU 20 pp1024 95.88 57.36 llama 8B all F32 29.92 GiB 8.03 B CPU 20 pp2048 85.46 53.26 llama 8B all F32 29.92 GiB 8.03 B CPU 20 pp4096 68.66 45.78 llama 8B all F32 29.92 GiB 8.03 B CPU 20 pp6144 57.35 40.44 25 ~ 30% improvement in llama-batched-bench with Metla-Llama3-8B in Prompt Processing Speed for large prompts (256, 512, 1024, 2048, 4096)tokens with various batch sizes ( 1, 2, 4, 8, 16) Signed-off-by: Shalini Salomi Bodapati <Shalini.Salomi.Bodapati@ibm.com>
…#15592) The original implementation unconditionally returned true for this operation, leading to a failure when the tensor's first dimension (ne[0]) was not a multiple of WARP_SIZE. This caused an GGML_ASSERT(ncols % WARP_SIZE == 0) failure in ggml-sycl/norm.cpp. This change updates the ggml_backend_sycl_device_supports_op check to correctly return true for GGML_OP_RMS_NORM only when the first dimension of the tensor is a multiple of WARP_SIZE, ensuring the operation can be performed without error.
* add fused group_norm/norm, mul, add * fix spacing * revert rms_norm logic * fix trailing whitespace
This commit updates the bash completion script to include the -m short option for the --model argument. The motivation for this is that currently tab completion only works the full --model option, and it is nice to have it work for the short option as well.
* ggml-cpu : add basic RVV support for vector f32 ops * ggml-cpu : add RVV support for f32 softmax
* CANN(flash-attn): refactor mask handling and improve performance 1. Refactored the mask computation in Flash Attention, unified the logic without separating prefill and decode. 2. Optimized performance in non-alibi scenarios by reducing one repeat operation. 3. Updated operator management to explicitly mark unsupported cases on 310P devices and when dim is not divisible by 16. Signed-off-by: noemotiovon <757486878@qq.com> * [CANN]: fix review Signed-off-by: noemotiovon <757486878@qq.com> * [CANN]: Optimization FA BNSD to BSND Signed-off-by: noemotiovon <757486878@qq.com> --------- Signed-off-by: noemotiovon <757486878@qq.com>
…e_context function for API Remoting
|
PR needs rebase. Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository. |
|
Caution Review failedThe pull request is closed. WalkthroughIntroduces new diffusion CLI and model-conversion tooling, extends chat formats (Granite, GPT-OSS), adds speculative drafting across incompatible vocabularies, broadens CLI/common params (diffusion, LR/optimizer, server/API), updates build/CI (Makefile stub, CMake presets, multiple workflows), revises Dockerfiles, refreshes docs/templates/labels, and adds ownership/config files. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
actor U as User
participant CLI as llama-diffusion-cli
participant L as LLaMA Model (ctx)
participant S as Samplers/CFG
U->>CLI: Invoke with model, prompt, diffusion params
CLI->>L: Load model + vocab, create context
CLI->>CLI: Tokenize/format input (optional chat template)
loop steps 1..N
CLI->>L: Decode (conditional/unconditional if CFG)
L-->>CLI: Logits
CLI->>S: Sample/top-k/p + algorithm scoring
S-->>CLI: Tokens to transfer/replace
CLI->>CLI: Update masked sequence
alt visual mode
CLI-->>U: Render progress/text
end
end
CLI->>L: Detokenize final tokens
L-->>CLI: Text
CLI-->>U: Output generated text + timings
sequenceDiagram
autonumber
actor App as Caller
participant Spec as common_speculative
participant T as Target ctx_tgt
participant D as Draft ctx_dft
App->>Spec: init(ctx_tgt, ctx_dft)
Spec->>Spec: Check vocab compatibility
App->>Spec: add_replacement_tgt_dft(map)
App->>Spec: gen_draft(prompt_tgt)
alt compatible vocab
Spec->>D: Decode on draft using target tokens
else incompatible
Spec->>Spec: Detokenize target → replace → retokenize for draft
Spec->>D: Decode on draft with prompt_dft
end
D-->>Spec: Draft tokens
alt incompatible
Spec->>Spec: Detokenize draft → replace → retokenize for target
end
Spec-->>App: Draft tokens in target vocab
Estimated code review effort🎯 5 (Critical) | ⏱️ ~120 minutes Possibly related PRs
Suggested reviewers
Poem
✨ Finishing Touches
🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
CodeRabbit Configuration File (
|
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: The full list of commands accepted by this bot can be found here.
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
79 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.
Summary by CodeRabbit