* Update to Torch 2.7.0
* Try to fix typer/click issue
* Pin click to fix incompatibility with typer
* Fix some test outputs with slight deviations
* Attempt again to sync with CI
* Mamba too
* Fixup mllama
Also switch to `unsloth/Llama-3.2-11B-Vision-Instruct` for testing
from the EU :).
* forward and tokenize chooser use the same shape
concate or filter happened to cpu tensor to avoid dynamic shape in hpu
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* use hpu set seed
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
---------
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* IPEX support FP8 kvcache
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* add kvcache dtype
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* add softcap and slidingwindow
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* kv scale in pageattn
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* remove triton installation, will be installed with torch
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* install xelink lib
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* softcap default -1.0
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* softcap default -1.0
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
---------
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* Add json_schema alias for GrammarType
* Add tests for all aliases
* fix: various linter adjustments
* fix: end-of-file-fixer lint
* fix: add test snapshots and avoid docs change
* fix: another end-of-file-fixer lint
* feat: support json_schema grammar constraining and add tests
* fix: bump openapi doc with new grammar option
* fix: adjust test payload
* fix: bump test snaps
---------
Co-authored-by: Alex Weston <alexw@alkymi.io>
* Add `.DS_Store` file to `.gitignore`
* Skip `{% generation %}` and `{% endgeneration %}`
Custom syntax within the chat template for the Phi4 Reasoning models
e.g. https://huggingface.co/microsoft/Phi-4-reasoning-plus, which is
AFAIK not handled natively yet, so skipping for now
* Update explanation on `{% generation %}` and `{% endgeneration %}` removal
* Revert "Add `.DS_Store` file to `.gitignore`"
This reverts commit d64d6d2f7f.
* clean cuda/rocm code in hpu backend, enable flat_hpu
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* fix TP in pageattn
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* adjust block table in hpu to improve performance
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* enable all the model. not testet yet
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* use tensor cache in hpu graph to avoid replay issue
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* add moe support, fix qwen/mistral/mixtral crash
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* fix phimoe issue
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* gpt_bigcode could also go pageattn
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* enable dbrx remove some unused code
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* multi-modality initial PR
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* adjust warmup and enable vlm
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* fix incorrect output in qwen2 idefics if hpu graph is used
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* remove unused quantization code and enable awq/gptq int4
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* fix gptq issue
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* enable fp8
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* warmup prefill
remove model where pageattn is not used, set block table to None since it's not used
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* add warmup_decode
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* warmup decode
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* remove block_tables and prefill_cache_indices which will lead to dynamic shape
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* fix comment
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* missing gptj change...
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* fix some issue
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* remove torch.where to fix incorrect output in hpu graph model
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* LLM warmup logic
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* multi-modality warmup
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* optimize code
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* refine log and fix some issue
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* fix warmup issue for mllama
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* pingpong optimization
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* match the latest vllm_extension ops
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* work with the latest vllm extension ops
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* remove block_scales which is not needed anymore
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* improve performance
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* prefill bypass graph
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* pingpong optimization issue fix
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
---------
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* add prometheus port
* fix doc
* add port for trtllm and llamacpp
* Fixing format after rebase.
---------
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
* launcher: ensure correct detection of Gemma 3 head size
* Support flashinfer for Gemma3 prefill
Gemma3 uses bidirectional attention for images. Flashinfer
supports custom masks. Hook up the mask with flashinfer, so that we do
not have to use the slower SDPA implementation for prefills with images.
* Update Gemma3 test outputs
* Fixed unused import
* transformers flash llm/vlm enabling in xpu
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* ipex cpu could also support in function
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
---------
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* clean cuda/rocm code in hpu backend, enable flat_hpu
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* fix TP in pageattn
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* adjust block table in hpu to improve performance
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* enable all the model. not testet yet
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* use tensor cache in hpu graph to avoid replay issue
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* add moe support, fix qwen/mistral/mixtral crash
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* fix phimoe issue
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* gpt_bigcode could also go pageattn
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* enable dbrx remove some unused code
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* multi-modality initial PR
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* adjust warmup and enable vlm
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* fix incorrect output in qwen2 idefics if hpu graph is used
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* remove unused quantization code and enable awq/gptq int4
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* fix gptq issue
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* enable fp8
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* warmup prefill
remove model where pageattn is not used, set block table to None since it's not used
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* add warmup_decode
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* warmup decode
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* remove block_tables and prefill_cache_indices which will lead to dynamic shape
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* fix comment
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* missing gptj change...
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* fix some issue
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* remove torch.where to fix incorrect output in hpu graph model
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* match the latest vllm_extension ops
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
---------
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
