In mult-brand GPU setups, if we couldn't fully load the model we
would fall through the scheduler and mistakenly try to load across
a mix of brands. This makes sure we find the set of GPU(s) that
best fit for the partial load.
This fixes various data races scattered throughout the download/pull
client where the client was accessing the download state concurrently.
This commit is mostly a hot-fix and will be replaced by a new client one
day soon.
Also, remove the unnecessary opts argument from downloadChunk.
This changes the registry client to reuse the original download URL
it gets on the first redirect response for all subsequent requests,
preventing thundering herd issues when hot new LLMs are released.
* Initial Batch Embedding
* Revert "Initial Batch Embedding"
This reverts commit c22d54895a280b54c727279d85a5fc94defb5a29.
* Initial Draft
* mock up notes
* api/embed draft
* add server function
* check normalization
* clean up
* normalization
* playing around with truncate stuff
* Truncation
* Truncation
* move normalization to go
* Integration Test Template
* Truncation Integration Tests
* Clean up
* use float32
* move normalize
* move normalize test
* refactoring
* integration float32
* input handling and handler testing
* Refactoring of legacy and new
* clear comments
* merge conflicts
* touches
* embedding type 64
* merge conflicts
* fix hanging on single string
* refactoring
* test values
* set context length
* clean up
* testing clean up
* testing clean up
* remove function closure
* Revert "remove function closure"
This reverts commit 55d48c6ed17abe42e7a122e69d603ef0c1506787.
* remove function closure
* remove redundant error check
* clean up
* more clean up
* clean up
This change fixes the handling of keep_alive so that if client
request omits the setting, we only set this on initial load. Once
the model is loaded, if new requests leave this unset, we'll keep
whatever keep_alive was there.
Users may not realize the siny new model they're trying to load
fits on their disk, but can't load into system+GPU memory. Today
we crash, but with this fix, we'll give them a better error message
before even trying to load it.
* OpenAI v1 models
* Refactor Writers
* Add Test
Co-Authored-By: Attila Kerekes
* Credit Co-Author
Co-Authored-By: Attila Kerekes <439392+keriati@users.noreply.github.com>
* Empty List Testing
* Use Namespace for Ownedby
* Update Test
* Add back envconfig
* v1/models docs
* Use ModelName Parser
* Test Names
* Remove Docs
* Clean Up
* Test name
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Add Middleware for Chat and List
* Completions Endpoint
* Testing Cleanup
* Test with Fatal
* Add functionality to chat test
* Rename function
* float types
* type cleanup
* cleaning
* more cleaning
* Extra test cases
* merge conflicts
* merge conflicts
* merge conflicts
* merge conflicts
* cleaning
* cleaning
---------
Co-authored-by: Attila Kerekes <439392+keriati@users.noreply.github.com>
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* OpenAI v1 models
* Refactor Writers
* Add Test
Co-Authored-By: Attila Kerekes
* Credit Co-Author
Co-Authored-By: Attila Kerekes <439392+keriati@users.noreply.github.com>
* Empty List Testing
* Use Namespace for Ownedby
* Update Test
* Add back envconfig
* v1/models docs
* Use ModelName Parser
* Test Names
* Remove Docs
* Clean Up
* Test name
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Add Middleware for Chat and List
* Testing Cleanup
* Test with Fatal
* Add functionality to chat test
* OpenAI: /v1/models/{model} compatibility (#5028)
* Retrieve Model
* OpenAI Delete Model
* Retrieve Middleware
* Remove Delete from Branch
* Update Test
* Middleware Test File
* Function name
* Cleanup
* Test Update
* Test Update
---------
Co-authored-by: Attila Kerekes <439392+keriati@users.noreply.github.com>
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
Previously, some costly things were causing the loading of GGUF files
and their metadata and tensor information to be VERY slow:
* Too many allocations when decoding strings
* Hitting disk for each read of each key and value, resulting in a
not-okay amount of syscalls/disk I/O.
The show API is now down to 33ms from 800ms+ for llama3 on a macbook pro
m3.
This commit also prevents collecting large arrays of values when
decoding GGUFs (if desired). When such keys are encountered, their
values are null, and are encoded as such in JSON.
Also, this fixes a broken test that was not encoding valid GGUF.
Until ROCm v6.2 ships, we wont be able to get accurate free memory
reporting on windows, which makes automatic concurrency too risky.
Users can still opt-in but will need to pay attention to model sizes otherwise they may thrash/page VRAM or cause OOM crashes.
All other platforms and GPUs have accurate VRAM reporting wired
up now, so we can turn on concurrency by default.
This adjusts our default settings to enable multiple models and parallel
requests to a single model. Users can still override these by the same
env var settings as before. Parallel has a direct impact on
num_ctx, which in turn can have a significant impact on small VRAM GPUs
so this change also refines the algorithm so that when parallel is not
explicitly set by the user, we try to find a reasonable default that fits
the model on their GPU(s). As before, multiple models will only load
concurrently if they fully fit in VRAM.
* API Show Extended
* Initial Draft of Information
Co-Authored-By: Patrick Devine <pdevine@sonic.net>
* Clean Up
* Descriptive arg error messages and other fixes
* Second Draft of Show with Projectors Included
* Remove Chat Template
* Touches
* Prevent wrapping from files
* Verbose functionality
* Docs
* Address Feedback
* Lint
* Resolve Conflicts
* Function Name
* Tests for api/show model info
* Show Test File
* Add Projector Test
* Clean routes
* Projector Check
* Move Show Test
* Touches
* Doc update
---------
Co-authored-by: Patrick Devine <pdevine@sonic.net>
While models are loading, the VRAM metrics are dynamic, so try
to load on a GPU that doesn't have a model actively loading, or wait
to avoid races that lead to OOMs
Our default behavior today is to try to fit into a single GPU if possible.
Some users would prefer the old behavior of always spreading across
multiple GPUs even if the model can fit into one. This exposes that
tunable behavior.
Still not complete, needs some refinement to our prediction to understand the
discrete GPUs available space so we can see how many layers fit in each one
since we can't split one layer across multiple GPUs we can't treat free space
as one logical block
