* server : include usage statistics only when user request them
When serving the OpenAI compatible API, we should check if
{"stream_options": {"include_usage": true} is set in the request when
deciding whether we should send usage statistics
closes: #16048
* add unit test
* llama-run: Fix model download on Windows
* fix SSL error (SSL peer certificate or SSH remote key was not OK)
* fix program crash on std::filesystem::rename
* llama-run: create a separate method to utilize RAII
* llama-run: handle rename exception
In `llama-perplexity`, when using `--kl-divergence`, the KL divergence statistics output mistakenly displays the 99th percentile twice. This change fixes that and correctly displays the 90th percentile as originally intended (presumably).
* ggml-backend : add GGML_BACKEND_DEVICE_TYPE_IGPU device type
ggml-backend : add device id to device props
llama : only use iGPU devices if there are no GPU devices
llama : do not use multiple devices from different backends with the same device id
* requirements : update transformers/torch for Embedding Gemma
This commit updates the requirements to support converting
Embedding Gemma 300m models.
The motivation for this change is that during development I had a local
copy of the transformers package which is what I used for converting
the models. This was a mistake on my part and I should have also updated
my transformers version to the official release.
I had checked the requirements/requirements-convert_legacy_llama.txt
file and noted that the version was >=4.45.1,<5.0.0 and came to the
conculusion that no updated would be needed, this assumed that
Embedding Gemma would be in a transformers release at the time
Commit fb15d649ed ("llama : add support
for EmbeddingGemma 300m (#15798)) was merged. So anyone wanting to
convert themselves would be able to do so. However, Embedding Gemma is
a preview release and this commit updates the requirements to use this
preview release.
* resolve additional python dependencies
* fix pyright errors in tokenizer test and remove unused import
* server : implement `return_progress`
* add timings.cache_n
* add progress.time_ms
* add test
* fix test for chat/completions
* readme: add docs on timings
* use ggml_time_us
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* feat: Add python-side constants and conversion for adapter.lora.invocation_string
Branch: gabe-l-hart/alora-support
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add c++ side constants for adapter.lora.invocation_string
Branch: gabe-l-hart/alora-support
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Parse invocation string for adapters from GGUF
Branch: gabe-l-hart/alora-support
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix(python): Update conversion to alora_invocation_tokens
This is the preferred method in PEFT which is the source of ground truth
https://github.com/huggingface/peft/pull/2609/files#diff-13380145401d203d5935c5189dd09879f990b81aa63e8e3aaff8ce9110333f0e
Branch: gabe-l-hart/alora-support
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix(cpp): Update to alora_invocation_tokens on c++ side
Branch: gabe-l-hart/alora-support
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add C APIs to get alora invocation token array from lora
Branch: gabe-l-hart/alora-support
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Initial implementation of alora cache logic in server
This does not yet do the part to identify the invocation tokens and only
apply the lora adapter afterwards, but it does seem to produce correct
results if the invocation tokens are the beginning of the uncached input.
Branch: gabe-l-hart/alora-support
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Identify alora invocation sequences
This currently limits to a single enabled alora per slot. Multiple aloras
with different invocation sequences would be possible, but it would require
a more complex integration of the adapter toggling and is not really a well
studied case for alora since it's unclear if one alora can reuse cache from
previous prefill computed with a different alora.
Branch: gabe-l-hart/alora-support
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Only reuse cache for tokens before the alora invocation start
This is a bit of an edge case, but theoretically a user could try the same
query with the alora disabled (just using the base model), then retry with
the alora. The cached tokens from the first pass should be invalid.
Branch: gabe-l-hart/alora-support
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Handle un-cached tokens that come before the alora activation
The solution is to only fill up to the token before the invocation start in
the batch if there are any tokens to be prefilled between those pulled from
cache and the invocation start. When this is detected, the alora is
temporarily disabled with a scale of 0.0, then immediately re-enabled after
it has been initialized for the internal graph. Since the batch does not
complete the prompt tokens, the remaining prompt tokens are handled in the
next task, pulling all of the non-alora tokens from cache and proceeding
with prefill for the alora tokens.
Branch: gabe-l-hart/alora-support
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Use || instead of 'or'
Too much python 🤦
Branch: gabe-l-hart/alora-support
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Fix off-by-one for limiting cached tokens to before alora start
This was the cause of the inconsistent results from the dummy test script
with and without the turn that runs the prompt without the adapter before
running it with the adapter.
Branch: gabe-l-hart/alora-support
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Support backwards-compatibility for "invocation_string" in adapter_config.json
While this has been replaced in the PEFT PR in favor of
alora_invocation_tokens, the existing adapters in the ibm-granite org on HF
use "invocation_string," so this will enable backwards compatibility and
enable testing now (before PEFT PR changes have percolated everywhere).
Branch: gabe-l-hart/alora-support
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Remove duplicate logging
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* feat: Report alora_invocation_string and alora_invocation_tokens from /lora-adapters
Branch: gabe-l-hart/alora-support
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
---------
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* feat: Set enable_thinking IFF not disabled and supported
Branch: gabe-l-hart/thinking-model-disabled-agent-prefill
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Fix inverted logic condition for prefill error
Branch: gabe-l-hart/thinking-model-disabled-agent-prefill
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Always parse the enable_thinking kwarg to overwrite the default value
From what I can tell, this started as a Qwen3-specific keyword, but from
the use in `chat.cpp` translates this inputs.enable_thinking to the right
thinking kwarg for the given model, this is now more of a standardized
kwarg, so it should always override the default value when sent as part of
the chat_template_kwargs field in the API.
Branch: gabe-l-hart/thinking-model-disabled-agent-prefill
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Don't limit tempalte expansion check to jinja
With the use_jinja check, non-jinja models would enable thinking and always
fail assistant prefill
Branch: gabe-l-hart/thinking-model-disabled-agent-prefill
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add the error text to json type errors in json_value
Branch: gabe-l-hart/thinking-model-disabled-agent-prefill
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Explicitly reject string values for "enable_thinking"
There are too many possible "truthy" / "falsy" strings and too many
ambiguous strings that don't have a clear truthy/falsy value, so the
simplest thing to do here is to reject the request. Ideally, this would be
a 422 (Unprocessable Entity), but right now it's coming back as a 500.
Branch: gabe-l-hart/thinking-model-disabled-agent-prefill
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: Move logic for detecting template enable_thinking support to common
Branch: gabe-l-hart/thinking-model-disabled-agent-prefill
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Use raw pointer for common chat template function
Branch: gabe-l-hart/thinking-model-disabled-agent-prefill
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
---------
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* sampling : optimize sorting using bucket sort in more places
ggml-ci
* sampling : do not sort in dist sampler
ggml-ci
* sampling : avoid heap allocations for sort buffers
ggml-ci
* common : add option to sort sampling candidates by probability
ggml-ci
* sampling : revert the change for preserving sort buffers
* sampling : use std::copy instead of memcpy
* sampling : clarify purpose of partial sort helpers
ggml-ci
* cont : remove wrong comment [no ci]
* common : update comment
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
---------
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* server : enable /slots by default and make it secure
ggml-ci
* server : fix tests to pass `--no-slots` when necessary
* server : extend /props with info about enabled endpoints
* Change to warn instead of debug, to explain reason for stopping.
* Update tools/main/main.cpp
Fix printing --2
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* 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
* 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
- Use server_tokens in more places in server and util.cpp
- Convert most functions that used llama_tokens to server_tokens
- Modify input tokenizer to handle JSON objects as subprompts
- Break out MTMD prompt parsing into utility function
- Support JSON objects with multimodal_data arrays for MTMD prompts along with other existing types
- Add capability to model endpoint to indicate if client can send multimodal data
- Add tests.
* Fix -Werror=return-type so ci/run.sh can run
* Update tools/mtmd/clip.cpp
Co-authored-by: Diego Devesa <slarengh@gmail.com>
* Remove false now that we have abort
---------
Co-authored-by: Diego Devesa <slarengh@gmail.com>
* Update docker.yml
修改docker.yml文件中的内容使其停止周期性的运行该workflow，如果想要运行该workflow可以手动启动
* feat:Modify the header file include path
1. There's no llava directory in the tools directory.
2. Because the command `target_include_directories(mtmd PUBLIC .)` is used in the `mtmd` CMakeLists.txt file, other targets that link against `mtmd` automatically include the `mtmd` directory as a search path for header files. Therefore, you can remove `target_include_directories(${TARGET} PRIVATE ../llava`` or use `target_include_directories(${TARGET} PRIVATE ../mtmd`` to explicitly require the `llama-server` target to use header files from `mtmd`.
* Restore the docker.yml file
Add tracking for high watermark cache usage and make it available in /metrics endpoint.
Use-case: Tracking largest needed cache usage under realistic workload
to better understand memory requirements and be able to adjust
cache size/quantization for model/cache accordingly.
* wip lfm2 vision model
* Fix conv weight
* Implement dynamic resolution
* Fix cuda
* support LFM2-VL-450M
* happy CI
* Remove extra `ggml_conv` and put others into the right place
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* model : add harmony parser for gpt-oss
* gpt-oss : fix grammar trigger from causing empty stack
* gpt-oss: tweak the grammar trigger again
* gpt-oss : add support for recipient in role header
* gpt-oss : fix ungrouped tool calls in grammar
* gpt-oss : loosen function name matching during parse
* gpt-oss : clean up workarounds
* gpt-oss : add template tests
* gpt-oss : simulate thinking and tool call tags
* gpt-oss : undo think tags when reasoning_format is none
* gpt-oss : set special tokens back to user defined
* gpt-oss : update openai-gpt-oss template
* server : filter out harmony thought messages
* gpt-oss : simplify parsing
