* feat: support qwen2.5 vl model
* fix: bump support models doc
* feat: check before rope type adjustment and small refactors
* fix: add transformer overlay for processor support
* fix: vendor processor and config from transformers
* fix: refactor/simplify conditionals
It's find in some machine. using hf_hub::api::sync::Api to download config is not successful which will make warmup fail since attribute like max_position_embeddings could not be got. update hf-hub to the latest version could fix it
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
Co-authored-by: Wang, Yi A <yi.a.wang@intel.com>
* Putting back the NCCL forced upgrade.
* .
* ...
* Ignoring conda.
* Dropping conda from the buidl system + torch 2.6
* Cache min.
* Rolling back torch version.
* Reverting the EETQ modification.
* Fix flash attention ?
* Actually stay on flash v1.
* Patching flash v1.
* Torch 2.6, fork of rotary, eetq updated.
* Put back nccl latest (override torch).
* Slightly more reproducible build and not as scary.
* fix Qwen VL break in intel platform
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* could use PositionRotaryEmbedding impl so rocm and ipex could all work
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
---------
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* Use Hub kernels for Marlin and cutlass quantization kernels
* Use hub kernels for MoE/GPTQ-Marlin MoE
* Use attention kernels from the Hub
* Cache the kernels in the Docker image
* Update moe kernels
* Support loading local kernels for development
* Support latest moe kernels
* Update to moe 0.1.1
* CI: download locked kernels for server tests
* Fixup some imports
* CI: activate venv
* Fix unused imports
* Nix: add attention/moe/quantization kernels
* Update hf-kernels to 0.1.5
* Update kernels
* Update tgi-nix flake for hf-kernels
* Fix EOF
* Take `load_kernel` out of a frequently-called function
* Hoist another case of kernel loading out of a somewhat hot function
* marlin-kernels -> quantization
* attention -> paged-attention
* EOF fix
* Update hf-kernels, fixup Docker
* ipex fix
* Remove outdated TODO
* Updating mllama after strftime.
* Town instead village.
* Forgot the integration snapshot.
* Attempt to fix intel CPU.
* Intel extension fix.
* Workaround intel.
* Moving those deps directly into pyproject.
* Revert "Moving those deps directly into pyproject."
This reverts commit 98c1496ea6.
* Non system uv.
* Fixing the docker environment hopefully.
* Missed a step.
* Move workdir up a bit.
* Bailing out of reproducible python env.
* Triton version.
* backend(trtllm): bump TRTLLM to v.0.17.0
* backend(trtllm): forget to bump dockerfile
* backend(trtllm): use arg instead of env
* backend(trtllm): use correct library reference decoder_attention_src
* backend(trtllm): link against decoder_attention_{0|1}
* backend(trtllm): build against gcc-14 with cuda12.8
* backend(trtllm): use return value optimization flag as as error if available
* backend(trtllm): make sure we escalade all warnings as errors on the backend impl in debug mode
* backend(trtllm): link against CUDA 12.8
* Using the "lockfile".
* Revert dummy modifications.
* Lock on python 3.11
* Another attempt.
* ..
* Bad cache hits.
* The good old monkey.
* How in the world...
* We need the launcher still.
* .
* ..
* Attempt #42
* Don't break all other builds.
* Mode max.
* Applying to other builds.
* feat: refactor model, improve startup and re enable tests
* fix: improve multimodal rotary embed caching
* fix: limit vision flop calc to qwen2 vl models and update config typing
* fix: include clippy lint
* feat: refactor position ids in warmup and bump tests
* fix: prefer default dtype
* fix: enable all cuda graphs and bump snapshots
* fix: adjust rotaty init path
* fix: simplify get position ids and remove usused vision config
* fix: update position ids so first dim is batch, simplify rotary and bump vlm default token limit
* fix: improve position id init during cuda warmup for mrope and simplfy rotary forward
* fix: check existance before accessing rope type in cuda warmup
* fix: check key before access
* fix: improve mrope check in cuda graph warmup
* fix: remove check for default rope type
* fix: add more test and improve model generation
* fix: improve and simplify get_cos_sin, refactors and cleanup get_position_ids
* fix: adjust signatures with types
* hotfix: fix trtllm CI build on release
* fix: test release.
* fix: test release.
* fix: test release. env not recognized https://github.com/actions/runner/issues/1661
* fix: test release. Works.
This version removes our patches/custom API. Makes it simpler to
get changes from upstream. One of which is that we can enable FP8
KV cache for paged attention as well.
* backend(trtllm): attempt to remove AWS S3 flaky cache for sccache
* backend(trtllm): what if we expose ENV instead of inline?
* backend(trtllm): and with the right env var for gha sccache
* backend(trtllm): relax the way to detect sccache
* backend(trtllm): make sccache definition manually
* backend(trtllm): ok let's try to define the launchers in build.rs when rustc_wrapper is present
* backend(trtllm): export env variable in run mb?
* backend(trtllm): Cache mode max to cache intermediate layers
* backend(trtllm): inject ompi_version build arg in dependent step
* Upgrade the version number.
* Remove modifications in Lock.
* Tmp branch to test transformers backend with 2.5.1 and TP>1
* Fixing the transformers backend.
inference_mode forces the use of `aten.matmul` instead of `aten.mm` the
former doesn't have sharding support crashing the transformers TP
support.
`lm_head.forward` also crashes because it skips the hook that
cast/decast the DTensor.
Torch 2.5.1 is required for sharding support.
* Put back the attention impl.
* Revert the flashinfer (this will fails).
* Building AOT.
* Using 2.5 kernels.
* Remove the archlist, it's defined in the docker anyway.
* backend(trtllm): update to 0.16.0
* backend(trtllm): do not use shallow clone
* backend(trtllm): use tag instead
* backend(trtllm): move to nvidia remote instead of hf
* backend(trtllm): reenable shallow clone
* backend(trtllm): attempt to use ADD instead of RUN for openmpi
* backend(trtllm): make sure we are using correct path for openmpi ADD in dockerfile
* backend(trtllm): add correctly untar it
