Sync Nexa's llama.cpp Fork with Upstream Updates #47
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
Signed-off-by: thxCode <thxcode0824@gmail.com>
* Add initial ggml cmake package * Add build numbers to ggml find-package * Expand variables with GGML_ prefix * Guard against adding to cache variable twice * Add git to msys2 workflow * Handle ggml-cpu-* variants * Link ggml/ggml-base libraries to their targets * Replace main-cmake-pkg with simple-cmake-pkg * Interface features require c_std_90 * Fix typo * Removed unnecessary bracket from status message * Update examples/simple-cmake-pkg/README.md Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update examples/simple-cmake-pkg/README.md Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
…gml-org#11422) Signed-off-by: rare-magma <rare-magma@posteo.eu>
* metal : use residency sets ggml-ci * metal : restore commandBufferWithUnretainedReferences calls [no ci] * metal : release descriptors ggml-ci * metal : check env GGML_METAL_NO_RESIDENCY ggml-ci * metal : fix build + clean-up ggml-ci
* ci : do not fail-fast for docker * build arm64/amd64 separatedly * fix pip * no fast fail * vulkan: try jammy
…-org#11441) This fixes segmentation fault error when running tests when no metal devices are available (for example, when not linked with Core Graphics framework or otherwise).
* impl::load change map bpe_ranks to onordered map for reduce time of impl::load on 30% * llama_model_loader::init_mapping - replace new llama_mmap to std::make_unique<llama_mmap> for clean code & reduce (/2) time of running init_mappings * Update src/llama-vocab.cpp --------- Co-authored-by: lexasub <empty@empty.ru> Co-authored-by: Diego Devesa <slarengh@gmail.com>
The value provided by minor doesn't include stepping for AMD, parse the value returned by gcnArchName instead to retrieve an accurate ID.
https://huggingface.co/docs/hub/en/ollama Signed-off-by: Eric Curtin <ecurtin@redhat.com>
The HTTP client in llama-run only prints an error in case the download of a resource failed. If the model name in the CLI parameter list is missing, this causes the application to crash. In order to prevent this, a check for the required model parameter has been added and errors for resource downloads get propagated to the caller. Signed-off-by: Michael Engel <mengel@redhat.com>
Implemented ggml_sycl_op_soft_max() F16 src1(mask) support for which a pragma deprecation warning was added during ggml-org#5021. To do this, had to decouple it from ggml_sycl_op_flatten which always considered src1 to be of fp32 type(many OP functions are dependent on it). * SYCL: SOFTMAX F16 mask support and other fixes * test-backend-ops: Add F16 mask test cases
Signed-off-by: rare-magma <rare-magma@posteo.eu>
Signed-off-by: rare-magma <rare-magma@posteo.eu>
As pulling protocols to llama-run Signed-off-by: Eric Curtin <ecurtin@redhat.com>
…le instantation bug (ggml-org#11080) This disables the workaround on rocblas fixed versions (>=4.0.0) to eliminate the runtime cost and unnecessary VRAM allocation of loading all tensile objects.
loops with bounds not known at compile time can not be unrolled. when ncols_template == 0, the bounds of the loop are not constexpr, thus llvm cant unroll the loops here.
* ci : fix build CPU arm64 * failed, trying ubuntu 22 * vulkan: ubuntu 24 * vulkan : jammy --> noble
…-org#11473) The test_completion_stream_with_openai_library() function is actually with stream=False by default, and test_completion_with_openai_library() with stream=True
Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
This commit enables the `--no-warmup` option for the llama-embeddings. The motivation for this change is to allow the user to disable the warmup when running the the program.
…(ggml/1065) some threads kept looping and failed to terminate properly after an abort during CPU execution. Co-authored-by: issi <issi@gmail.com>
* Add option to not print stack on abort Add option/envvar to disable stack printing on abort. Also link some unittests with Threads to fix link errors on ubuntu/g++11. * Update ggml/src/ggml.c --------- Co-authored-by: Diego Devesa <slarengh@gmail.com>
People search for ollama models using the web ui, this change allows one to copy the url from the browser and for it to be compatible with llama-run. Signed-off-by: Eric Curtin <ecurtin@redhat.com>
…gml-org#11436) * vulkan: Catch pipeline creation failure and print an error message Also, fix some warnings from my on-demand compile change. * vulkan: fix pipeline creation logging
* server : update auto gen files comments This commit updates the 'auto generated files' comments in server.cpp and removes `deps.sh` from the comment. The motivation for this change is that `deps.sh` was removed in Commit 91c36c2 ("server : (web ui) Various improvements, now use vite as bundler (ggml-org#10599)"). * squash! server : update auto gen files comments [no ci] Move comments about file generation to README.md. * squash! server : update auto gen files comments [no ci] Remove the comments in server.cpp that mention that information can be found in the README.md file.
…-org#11360) * vulkan: initial support for IQ3_S * vulkan: initial support for IQ3_XXS * vulkan: initial support for IQ2_XXS * vulkan: initial support for IQ2_XS * vulkan: optimize Q3_K by removing branches * vulkan: implement dequantize variants for coopmat2 * vulkan: initial support for IQ2_S * vulkan: vertically realign code * port failing dequant callbacks from mul_mm * Fix array length mismatches * vulkan: avoid using workgroup size before it is referenced * tests: increase timeout for Vulkan llvmpipe backend --------- Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
Davidqian123
approved these changes
Mar 5, 2025
github-actions
bot
added
documentation
Davidqian123
approved these changes
Mar 5, 2025
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.
Description
This pull request updates Nexa's llama.cpp fork to incorporate the latest upstream changes (commit 06c2b1)) while preserving Nexa-specific modifications.
Key Updates
./common/to align with llama.cpp changes.