| Age | Commit message (Collapse) | Author |
|---|
|
|
|
Take all dependencies from the cross stage, rather tha only stdenv
|
|
- The generic /usr/bin/env shebangs are good enough
- Python deps are provisioned in the devShells
- We need to be able to leave python out at least on windows (currently breaks eval)
|
|
initial nix build for windows using zig
mingwW64 build
removes nix zig windows build
removes nix zig windows build
removed unnessesary glibc.static
removed unnessesary import of pkgs in nix
fixed missing trailing newline on non-windows nix builds
overriding stdenv when building for crosscompiling to windows in nix
better variables when crosscompiling windows in nix
cross compile windows on macos
removed trailing whitespace
remove unnessesary overwrite of "CMAKE_SYSTEM_NAME" in nix windows build
nix: keep file extension when copying result files during cross compile for windows
nix: better checking for file extensions when using MinGW
nix: using hostPlatform instead of targetPlatform when cross compiling for Windows
using hostPlatform.extensions.executable to extract executable format
|
|
|
|
|
|
* server: bench: init
* server: bench: reduce list of GPU nodes
* server: bench: fix graph, fix output artifact
* ci: bench: add mermaid in case of image cannot be uploaded
* ci: bench: more resilient, more metrics
* ci: bench: trigger build
* ci: bench: fix duration
* ci: bench: fix typo
* ci: bench: fix mermaid values, markdown generated
* typo on the step name
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
* ci: bench: trailing spaces
* ci: bench: move images in a details section
* ci: bench: reduce bullet point size
---------
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
|
|
Until https://github.com/ggerganov/llama.cpp/issues/6346 is resolved
|
|
|
|
|
|
* embedding : show full embedding for single prompt
To support the use case of creating an embedding for a given prompt, the entire embedding and not just the first part needed to be printed.
Also, show cosine similarity matrix only if there is more than one prompt, as the cosine similarity matrix for a single prompt is always `1.00`.
* Update examples/embedding/embedding.cpp
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
|
|
* Fix batched impl
* Maintain previous behaviour for igpu
* retrigger CI
---------
Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
|
|
* iq1_m: make it work for QK_K = 64 (WIP)
* iq1_m: make it work for QK_K = 64 (scalar and AVX2)
* iq1_m: QK_K = 64 seems to work on Metal and ARM_NEON
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
|
|
* Change --no-penalize-nl to --penalize-nl
* Update documentation too
|
|
|
|
* add php bindings to readme
* readme : add link to PR
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
|
|
server: public: support custom `api_url`, default to relative base path
|
|
|
|
Also use C locale for ispunct/isspace, and split unicode-data.cpp from unicode.cpp.
|
|
* llama : greatly reduce logits memory usage
* llama : more compact state saving and reloading
* llama : fix lctx.n_outputs not being set before building graph
* perplexity : adapt to the logits API changes
* perplexity : fix Winogrande, use correct logits for second choice start
The first logits used to evaluate the second choice were not from
the end of the common prefix; instead, they were the logits from the end
of the first choice. This has been corrected.
The previous implementation sometimes had outliers in the scores of
choices for some tasks, and the logic to skip choices words
in the log-likelihood evaluation probably was an attempt to reduce those,
but it was complex and didn't quite seem to be the right thing.
This is simpler now, and the outlier scores aren't there anymore.
* perplexity : normalize spaces and punctuation in Winogrande sentences
* llama : fix embedding conditions
* llama : fix llama_get_embeddings_ith when the resulting id is 0
* llama : fix wrong n_outputs in llama_set_inputs
A mismatch happened when using a smaller n_ubatch than n_batch and then using
llama_batch_get_one(). The decision of what n_outputs should be now almost
fully depends on how lctx.n_outputs is set in llama_decode_internal.
The conditions are simpler this way.
* llama : when saving the state, recalculate n_outputs
This ensures the correct number of outputs for the entire previous batch
is stored in the session file, even when n_ubatch is smaller than n_batch.
* llama : fix not-skipping outputs of non-causal models
* llama : fix running a batch with n_outputs == 0
It previously worked because lctx.inp_out_ids was not initialized,
so it pointed to some garbage address which was somehow still valid when I
ran my tests.
* llama : keep same graph topology even when n_outputs == 0
* ggml : saner ggml_can_repeat with empty tensors
* ggml : future-proof ggml_is_empty by using GGML_MAX_DIMS - 1
* ggml : do not multi-thread ops returning empty tensors
* ggml : make ggml_is_empty public and work with views
* llama : use a vector for ctx->output_ids
* llama : rework reallocation logic for llama_output_reserve
Now comparing the actual size with the new total size of the output buffer
to allow more efficient enabling and disabling of the embeddings
and/or logits output in the future.
* ggml : skip empty tensors in all backends
* llama : fix llama_output_reserve nullptr deref when new_size is 0
* perplexity : make Winogrande work as it does on master
The problems with the Winogrande implementation will
need to be fixed in a separate PR to ease review.
* llama : clearer error messages for invalid logits or embeddings ids
* llama : assert all models that can have inp_out_ids
Since the graph topology is now constant, this presence check
can be done even when there are no outputs.
* llama : assert logits and embd buffers exist before writing to them
* llama : handle errors from llama_output_reserve at call sites
* perplexity : make hellaswag and multiple-choice outputs identical to master
Due to how the KV cache is updated, the logprobs for tokens in a batch
are very slightly affected by the other tokens present in the batch,
so to make hellaswag and multiple-choice return exactly the same results
as on master, the last token of each sequence needs to be evaluated
even though its output is not used at all.
This will probably be changed back in the future to make these benchmarks
a tiny bit faster.
* perplexity : fix division by zero when using less than 100 multiple-choice tasks
* llama : allow loading state saved with a different ctx size
When loading a session file, the context size is now only required to be
at least enough to load the KV cells contained in that session file,
instead of requiring to use exactly the same context size as when saving.
Doing this enables the use-case of extending or shrinking the context size
of a saved session.
This breaks existing session files because the meaning of kv_buf_size
is slightly changed (previously it was the size of the whole KV cache,
now it's only the size of the saved part of it). This allows for
finer-grained sanity checks when loading in an effort to keep kv_buf_size
useful even when the kv_size is changed.
* llama : minor
ggml-ci
* readme : update recent API changes, and warn about Vulkan
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
|
|
* iq1_m: basics
* iq1_m: basics-2
* iq1_m: CUDA dequantize works
Very 1st shot I get PPL = 9.76 for LLaMA-v2-7B.
* iq1_m: separate shifts for each group of 8 in a block
We get
PPL(LLaMA-v2-7B ) = 9.2810
PPL(LLaMA-v2-13B) = 6.8105
Not bad, but slightly higher than
sqrt(PPL(IQ1_S) * PPL(IQ2_XXS))
which is the expected outcome given that IQ1_M is
halfway between IQ1_S and IQ2_XXS in terms of bpw.
From this, we would expect
PPL = 9.14 for LLaMA-v2-7B
PPL = 6.63 for LLaMA-v2-13B
* iq1_m: go to 3-bit scales
There is slight increase in PPL, but the 0.0625 bpw reduction
in size is totally worth it.
We now have
PPL(LLaMA-v2-7B ) = 9.4469 at 1.96 bpw
PPL(LLaMA-v2-13B) = 6.8717 at 1.93 bpw
PPL(LLaMA-v2-70B) = 4.8568 at 1.85 bpw
* iq1_m: scalar dot product
* iq1_m: AVX2 dot product
* iq1_m: very slightly faster AVX2 dot product
* iq1_m: ARM_NEON dot product
Works, but very slow (10.5 t/s)
* iq1_m: Metal - dequantize works, dot product does not
* iq1_m: Metal now works
About the same performance as iq1_s.
* iq1_m: minor
* iq1_m: checking pure iq1_m quantization
It is pretty bad: PPL(LLaMA-v2-7B) = 34 if we quantize output.weight
with Q4_K.
* iiq1_m: slightly faster ARM_NEON dot product
10.5 t/s -> 11.65 t/s
* iq1_m: faster ARM_NEON dot product
11.65 t/s -> 14.9 t/s
* iq1_m: another minor ARM_NEON dot product improvement
14.9 -> 15.0 t/s
* iq1_m: small PPL improvement via super-block scale adjustment
After quantizing block scales redo the super-block scale fit.
PPL(LLaMA-v2-7B ) = 9.3346
PPL(LLaMA-v2-13B) = 6.8419
PPL(LLaMA-v2-70B) = 4.8294
PPL(Mistral-7B ) = 8.1624
* iq1_m: adapt to CUDA refactoring
* iq1_m: remove unused variable
We have progressed to warnings being errors.
* iq1_m: add to backend-ops tests
* iq1_m: fix Windows ARM
* iq1_m: use common definition of iq1m_scale_t
* cuda: assert -> NO_DEVICE_CODE
* iq1_M: PR comments
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
|
|
|
|
* quantize: be able to override metadata by key
* minor : spacing
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
|
|
* embedding: assign `n_ubatch` value, print error on `n_batch` overflow
* Update examples/embedding/embedding.cpp
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
* use %ld instead of %lld
* Revert "use %ld instead of %lld"
This reverts commit ea753ede90a86a0699f65878cc8e2020ff5eabb8.
---------
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
|
|
|
|
* Symlink to /usr/bin/xcrun so that `xcrun` binary
is usable during build (used for compiling Metal shaders)
Fixes https://github.com/ggerganov/llama.cpp/issues/6117
* cmake - copy default.metallib to install directory
When metal files are compiled to default.metallib, Cmake needs to add this to the install directory so that it's visible to llama-cpp
Also, update package.nix to use absolute path for default.metallib (it's not finding the bundle)
* add `precompileMetalShaders` flag (defaults to false) to disable precompilation of metal shader
Precompilation requires Xcode to be installed and requires disable sandbox on nix-darwin
|
|
|
|
Since no blas was provided to buildInputs, the executable is built without blas support.
This is a backport of NixOS/nixpkgs#298567
|
|
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
|
|
Flake lock file updates:
• Updated input 'nixpkgs':
'github:NixOS/nixpkgs/d691274a972b3165335d261cc4671335f5c67de9' (2024-03-14)
→ 'github:NixOS/nixpkgs/44d0940ea560dee511026a53f0e2e2cde489b4d4' (2024-03-23)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
|
|
|
|
|
|
* server: clean up oai parsing function
* fix response_format
* fix empty response_format
* minor fixes
* add TODO for logprobs
* update docs
|
|
* fix LOG() error for SYCL, enhance erro check by CI
* rollback to bash
* add newline at end of file
|
|
* add `retrieval` example
* add README
* minor fixes
* cast filepos on print
* remove use of variable sized array
* store similarities in separate vector
* print error on insufficient batch size
* fix error message printing
* assign n_batch value to n_ubatch
* fix param definitions
* define retrieval-only parameters in retrieval.cpp
* fix `--context-file` option to be provided multiple times for multiple files
* use vector for `query_emb`
* add usage description in README
* fix merge conflict
* fix usage printing
* remove seed setting
* fix lint
* increase file read buffer size
* retrieval : minor
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
|
|
This change causes some quants (e.g. Q4_0, Q8_0) to go faster on some
architectures (e.g. AMD Zen 4).
|
|
* would throw error on VS2022 on GGML_FREE(wmode)
* wchar_t is usually 2 bytes, but malloc wants bytes
* therefore `*wmode_p++ = (wchar_t)*mode;` could write off the end of the allocation
* Fixes error possibly introduced by https://github.com/ggerganov/llama.cpp/pull/6248
|
|
* imatrix : fix wname for mul_mat_id ops
* also filter tensor names in mul_mat_id ops
---------
Co-authored-by: slaren <slarengh@gmail.com>
|
|
|
|
|
|
* sampling: remove duplicated code for probability distribution access
* free original_logits
* fix original_logits allocation
* fixes based on review @cebtenzzre
* change function name to `llama_sampling_prepare`
|
|
* remove no USM methods
* leave the schedule to ggml_backend_sched entirely
|
|
* support release win
* fix value
* fix value
* fix value
* fix error
* fix error
* fix format
|
|
also fix missing #defines before windows.h, and BPE LF token on MSVC
|
|
|
|
* llama: llama_split_prefix fix strncpy does not include string termination
common: llama_load_model_from_url:
- fix header name case sensitive
- support downloading additional split in parallel
- hide password in url
* common: EOL EOF
* common: remove redundant LLAMA_CURL_MAX_PATH_LENGTH definition
* common: change max url max length
* common: minor comment
* server: support HF URL options
* llama: llama_model_loader fix log
* common: use a constant for max url length
* common: clean up curl if file cannot be loaded in gguf
* server: tests: add split tests, and HF options params
* common: move llama_download_hide_password_in_url inside llama_download_file as a lambda
* server: tests: enable back Release test on PR
* spacing
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* spacing
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* spacing
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
|
|
(#6254)
|
|
* Add support for Grok model architecture
* Revert convert-hf-to-gguf to default options
* Fixed f_norm_rms_eps bug
* Fix whitespaces
* llama : fix grok rope type
* llama : minor
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
|
|
|
|
|
