GitLab

* Fix: don't apply post layernorm in SiglipVisionTransformer

This fixes a bug with LLaVA Next when using Siglip as the vision model. LLaVA Next expects the output of the vision model to be the encoder outputs before layernorm (see original transformers implementation here: https://github.com/huggingface/transformers/blob/main/src/transformers/models/llava_next/modeling_llava_next.py#L813).

This also makes Siglip consistent with the existing Clip implementation:

https://github.com/huggingface/text-generation-inference/blob/main/server/text_generation_server/models/custom_modeling/clip.py#L613



* fix: adjust pali gemma for post layer norm and small refactors

---------
Co-authored-by: Travis Addair <tgaddair@gmail.com>

* Prefix caching WIP

* Fixing prefix attention.

* Fixing flashinfer import.

* Fixing black.

* Fixing medusa (still wrong outputs, but functional).

* Just medusa values now.

* Fixing medusa without prefix caching.

* Fixing prefix caching.

* Medusa requires reshaping.

* Removing the logs.

* Remove router.nix

* Fixup:

- Remove logs
- Disable VLMs (they do not work)
- Disable prefix caching when user wants prefill logprobs.

* Update flake.lock

---------
Co-authored-by: Daniël de Kok <me@danieldk.eu>

* Fixing exl2 and other quanize tests again.

* Mark exl2 as non release (so CI tests them, needs to be removed latet).

* Fixing exl2 (by disabling cuda graphs)

* Fix quantization defaults without cuda graphs on exl2 (linked to new
issues with it).

* Removing serde override.

* Go back to released exl2 and remove log.

* Adding warnings for deprecated bitsandbytes + upgrade info to warn.

* Upgrading exl2.

* Fixing the other pathways.

* Fix idefics.

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* feat: validate template variables before apply and improve sliding window check

* fix: improve missing template var test

This change adds support for prefix caching to the v3 router. This
is broken up from the backend support to ease reviewing.

For now prefix caching is only enabled with `USE_PREFIX_CACHING=1`
in this case, the router will switch to `RadixAllocator`. This
allocator uses a radix trie to keep track of prefills that were
seen prior. If a new prefill is a prefix of a previously-seen
prefil, the router will send a request with `prefix_len>0`, which
can be used by the backend to decide to reuse KV blocks from the
cache, rather than recomputing them.

Even though backend support is not added in this PR, the backend
will still work with prefix caching enabled. The prefix lengths
are just ignored and not used.

* Using an enum for flash backens (paged/flashdecoding/flashinfer)

* Early exit on server too.

* Clippy.

* Fix clippy and fmt.

* Minor doc fixes

* up.

* Other minor updates.

This change adds support for FlashInfer. FlashInfer can be enabled using
`FLASH_INFER=1` and is currently only implemented in `FlashCausalLM`.
Since this functionality is currently only for testing, FlashInfer is
not installed anywhere yet.

The FlashInfer API is quite different from FlashAttention/vLLM in that
it requires more global bookkeeping:

* A wrapper class needs to be contstructed (which we just call *state*).
  Since this is fairly expensive (due to pinned host memory allocation),
  we only do this once in a FlashCausalLM instance or for each CUDA
  Graph size.
* Each model forward call needs to be wrapped in `begin_forward` and
  `end_forward`. This sets up data structures that can be reused for all
  calls to attention for that forward call.

When calling attention, we need access to the state object. To avoid
passing an argument down the call chain (which would require changes to
all models), we use a context variable.

Each model forward call is wrapped using a context manager that does all
the bookkeeping for such a call:

* Set the context variable to the forward call's state.
* Call `begin_forward` on the state.
* Yield.
* Call `end_forward` on the state.
* Reset the context variable.

We cannot use a single shared global variable for this, since e.g. CUDA
Graphs of different sizes each have their own state.

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* Update __init__.py

Fix issue with NoneType comparison for max_input_tokens and sliding_window

- Add default values for max_input_tokens and sliding_window to handle None cases.
- Ensure the comparison between max_input_tokens and sliding_window is handled correctly to prevent TypeError.
- This change addresses the error: TypeError: '<=' not supported between instances of 'int' and 'NoneType'.

* Update __init__.py

Handle NoneType in sliding_window comparison to fix TypeError in __init__.py by ensuring the comparison logic accounts for NoneType values, preventing errors and improving code robustness.

* fix: syntax/style tweak

---------
Co-authored-by: Praz <prazanth2006@gmail.com>

* Fix the bug

* fix: run lints

* fix: small syntax tweak

---------
Co-authored-by: Sadra Barikbin <sadraqazvin1@yahoo.com>

* add gptj modeling
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix: update docs for model addition

* fix: adjust syntax typo

* fix: adjust syntax typo again

---------
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
Co-authored-by: Wang, Yi A <yi.a.wang@intel.com>

Co-authored-by: Islam Almersawi <islam.almersawi@openinnovation.ai>

* fix: attempt forward on flash attn2 to check hardware support

* fix: warn window_size_left when using flash attn 1

* fix: prefer version check over test op and avoid window_size_left if not flash attn2

* fix: improve condtional and error message

* fix: update sliding window conditional

* fix: simplify changes and revert model changes

* fix: avoid changing conditional

* fix: typo tweak

- Always return the hidden states.
- Create the output tensor inside the `attention` and `paged_attention`
  functions.

This removes the difference between how the output is handled between
attention (output parameter) and paged attention (return value). This
also removes the assumption that the attention implementation can
write to an output tensor (in preparation of FlashInfer).

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* MODEL_ID propagation fix

* fix: remove global model id

---------
Co-authored-by: root <root@tw031.pit.tensorwave.lan>

* feat: add ruff and resolve issue

* fix: update client exports and adjust after rebase

* fix: adjust syntax to avoid circular import

* fix: adjust client ruff settings

* fix: lint and refactor import check and avoid model enum as global names

* fix: improve fbgemm_gpu check and lints

* fix: update lints

* fix: prefer comparing model enum over str

* fix: adjust lints and ignore specific rules

* fix: avoid unneeded quantize check

* fix: refactor adapter weight loading and mapping

* feat: enable lora load from directory

* fix: adjust launcher for local lora adapters

* feat: improve weight loading and add tests

* fix: improve logging and rebase syntax issue

* fix: impove adapter merge comments and remove unused conditional

* fix: improve get_model_with_lora_adapters naming

* fix: comment typo

fix of use of unquantized weights in cohere GQA loading, also enable the model in intel platform
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix crash in multi-modal
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* update according to review comment
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix llava_next regression in latest main
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

---------
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* Support passing head_dim through config

* Using `head_dim` as a fallback is necessary since it's a non standard
key in mistralConfig (as defined in transformers).

* Shorter diff.

---------
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>

* Softcapping for gemma2.

* Less clutter.

* No access to transformers config, only config_dict here.

* 0.0 is the null value in the C++ API.

* fix(server): fix fp8 weight loading

* fixed scales loading

* update snap

* revert default dtype

* Update idefics_causal_lm.py

Fix syntax issues

* fix dbrx & opt model prefix bug

* Hotfix: fix of use of unquantized weights in Mixtral GQA loading

* feat(fp8): add support for fbgemm

* allow loading fp8 weights directly

* update outlines

* fix makefile

* build fbgemm

* avoid circular import and fix dockerfile

* add default dtype

* refactored weights loader

* fix auto conversion

* fix quantization config parsing

* force new nccl on install

* missing get_weights implementation

* increase timeout

Deepseek V2 is a MoE model from Deepseek. Relevant variations
compared to other models:

- Grouped top-K in expert selection.
- mscale in yarn is calculated using the `mscale` and `mscale_all_dim`
  configuration options.
- `mscale_all_dim` is also used in scaling attention softmax.
- Permuting of the query/key representations before applying rotary
  embeddings.
- Some projections cannot be sharded (`q_a_proj`, `kv_a_proj_with_mqa`).
  So, we need weight loads that supports quantized weights. To this
  end `{Weights,WeightLoader}.get_weight` was added.
- The query/key head dimensionality differs from that of the value,
  so we need to pad during attention.
- Heads with size 192, needs an extension to our paged attention
  fork and we need to ensure that the KV cache is allocated with the
  correct size.
- Shared experts.

* Improve the handling of quantized weights

Handling of quantized weights was split between two mechanisms:

- For quantized checkpoints, we used the new weight loader
  infrastructure.
- For quantization while loading (EETQ, FP8, bitsandbytes) we
  instead relied on conditional in `get_linear`.

Weight loaders support context managers to selectively load
particular layers with different weight loaders, which is useful
for models like Idefics2 AWQ, which uses a quantized text model,
but unquantized vision and connector models. However, the context
manager would be overrided by `get_linear`, which string-checks
`quantizer`. Also, the context manager would not work with
EETQ, FP8, and bitsandbytes.

This change migrates all quantizers to the weight loader infrastructure.
This has several benefits:

- We can use context managers with all quantizers.
- All the implementation details move down to the quantizer layers,
  `get_linear` does not need to know how to handle quantizer linear
  layers.
- All quantizer weights are strongly typed, we don't pass around
  raw tensors.
- We don't have to pass around the `quantizer` string everywhere.

* Exclude non-MLP layers when using FP8 quantization with Llama