merge from upstream #14
Merged
Conversation
This file contains 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
…v#6688) * Implement '--keep-split' to quantize model into several shards * Add test script * Update examples/quantize/quantize.cpp Co-authored-by: Georgi Gerganov <[email protected]> * Split model correctly even if tensor id is out-of-order * Update llama_model_quantize_params * Fix preci failures --------- Co-authored-by: z5269887 <[email protected]> Co-authored-by: Georgi Gerganov <[email protected]>
* tests : minor bash stuff ggml-ci * llama : fix build ggml-ci * tests : fix CUR_DIR -> ROOT_DIR ggml-ci * tests : fix fname ggml-ci
This commit renamesthe lerp (linear interpolation) function in clip.cpp to avoid a conflict with the lerp function in the <cmath> standard C++ library when using c++20. The motivation for this change is to enable projects that use c++20 to be able to compile clip.cpp without having to resort to patching it. The lerp function was added to cmath in version C++20 (202002L) and is why this is not causing any issue at the moment as C++11/C++17 is currently used by llama.cpp. I realize that llama.cpp uses either C++11 (or C++17 in the case for SYCL) but wanted to ask if this would be an acceptable change just the same. Refs: https://en.cppreference.com/w/cpp/numeric/lerp Signed-off-by: Daniel Bevenius <[email protected]>
…v#6885) * llama : check that all the tensor data is in the model file * also check for unsigned overflow
* Update README.md * missing space * llama3 !
* add support for moondream vision language model This required making the following changes to the CLIP model: 1. Support for patch embedding bias. 2. Make class embedding and pre-layernorm optional. 3. Add support for post-layernorm. * Update examples/llava/clip.cpp --------- Co-authored-by: Georgi Gerganov <[email protected]>
* always use calloc clamp n_kv on failure to read a kv * ggml : alternative ctx->header.n_kv update --------- Co-authored-by: slaren <[email protected]>
…gerganov#6638) * server: cap n_predict if not set to n_ctx_train * server: fix infinite loop * server: infinite loop, move in process_token server: infinite loop: set stop limit to true * minor: spaces * minor: spaces * server: include prompt tokens in the EOS limit
* add basic tensor data validation function * add --check-tensors command line argument tensor validation is disabled by default and can be enabled by adding `--check-tensors` to the command line arguments. quantize always validates tensors.
* imatrix: save the dataset file used in the output file * llama: support kv overrides type string string * common: factorize KV Overrides parsing between common and server * quantize: add imatrix n entries and dataset KV metadata quantize: factorize KV Overrides parsing between common ggerganov#6656 * llama: remove kv override str_value initialization as it does not compile on some toolchain * quantize: add imatrix m_last_call as `quantize.imatrix.chunks_count` * quantize: add imatrix filename in KV * llama: add llama_model_kv_override_free * common: add llama_model_kv_override_free common: free kv override if used after model loading * llama: finally move the string KV override value to the stack * llama : minor * no need to add a NUL to the std::vector, std::string can be initialized from a pair of iterators. Co-authored-by: slaren <[email protected]> * kv override: ensure string termination --------- Co-authored-by: Georgi Gerganov <[email protected]> Co-authored-by: slaren <[email protected]>
…n device (ggerganov#6933) * Reset schedule earlier to allow overlap with graph computation on device
…n_predict (ggerganov#6935) * ci: server: fix python env * ci: server: fix server tests after ggerganov#6638 * ci: server: fix windows is not building PR branch
Flake lock file updates:
• Updated input 'nixpkgs':
'github:NixOS/nixpkgs/5c24cf2f0a12ad855f444c30b2421d044120c66f?narHash=sha256-XtTSSIB2DA6tOv%2Bl0FhvfDMiyCmhoRbNB%2B0SeInZkbk%3D' (2024-04-19)
→ 'github:NixOS/nixpkgs/7bb2ccd8cdc44c91edba16c48d2c8f331fb3d856?narHash=sha256-Drmja/f5MRHZCskS6mvzFqxEaZMeciScCTFxWVLqWEY%3D' (2024-04-25)
Co-authored-by: arthw <>
* not allow adding duplicated tensor name * no duplicated tensor while reading gguf * typo * throw exception inside llama_model_loader Co-authored-by: slaren <[email protected]> --------- Co-authored-by: slaren <[email protected]>
* Fix more int overflow during quant. * Fix some more int overflow in softmax. * Revert back to int64_t.
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.