GitLab

* Choosing input/total tokens automatically based on available VRAM?

* Update doc.

* Remove generated files.

* Trying to fix non chunking targets.

* Attempt #2

* fix.

* QuantLinear is rocm compatible.

* Much simpler logic after the overhead.

* Updating logic + non flash.

* Revert doc text.

* Simple updates.

* Fix integration mt0 (transformers update).

* feat: add triton kernels to decrease latency of large batches

* cast to int32

* fix kernel

* fix kernel

* disable triton on rocm

* fix speculation

* add slots filtering kernel

* Switch from fbgemm-gpu w8a8 scaled matmul to vLLM/marlin-kernels

Performance and accuracy of these kernels are on par (tested with Llama
70B and 405B). Removes a dependency and resolves some stability issues
we have been seeing.

* Update test snapshots

* Add support for FP8 KV cache scales

Since FP8 only has limited dynamic range, we can scale keys/values
before storing them into the cache (and unscale them in attention). To
avoid rescaling the cache as the absmax values change, good scales are
usually determined per layer using calibration calibration data and stored
in the checkpoint.

This change adds support for for using key-value scales and loading them
from checkpoints in the two most common formats:

- Separate per-layer `k_scale` and `v_scale` scalars.
- Per-layer `kv_scale` scalar (older format).

Currently, scales are only used with an `float8_e4m3fn` cache.

Besides adding support for key/value scales, the `fp8_quantize` function
is also extended to support quantization with a kernel vendored from
vLLM. This is slightly faster than the PyTorch implementation, but also
scales in FP32, potentially improving accuracy.

* Update FP8 KV cache test to use checkpoint with scales

* `can_scale`: check that the attention is flashinfer

* feat: natively support Granite models

* Update doc

Change `fp8_quantize` so that we can pass around reciprocals everywhere,
so scales are always passed around in the checkpoint format.

I also noticed that we ignore any input scales that we might have when
fbgemm is available. Skip this path if we already have a scale.

* add gptq and awq int4 support in intel platform
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

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

* set kv cache dtype
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* refine the code according to the review command
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* Simplifying conditionals + reverting integration tests values.

* Unused import

* Fix redundant import.

* Revert change after rebase.

* Upgrading the tests (TP>1 fix changes to use different kernels.)

* Update server/text_generation_server/layers/gptq/__init__.py

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

* fix: prefer inplace softmax to avoid copy

* Update server/text_generation_server/models/flash_causal_lm.py
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>

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

* Simplify the `attention` function

- Use one definition rather than multiple.
- Add `key`/`value` arguments, so that we don't need the
  `PREFILL_IN_KVCACHE` constant.
- Make it kwargs-only (to avoid mixing up the various `Tensor` args).

* Fixup flashinfer support

* Support `e4m3fn` KV cache

* Make check more obvious

* wip

* rollback

* refactor to use prefix/postfix namming + fix all_input_ids_tensor

* maybe patching vlms?

* fix filter and concat

* wip, no filter, no concat

* current

* add prepare_for_prefill

* working

* load tested

* re-create slots

* re-create slots

* fix slot_filtering_indices

* feedback loop

* remove log

* fix benchmarker

* fix vlm and seq2seq

* rename to cache and input lengths

* fix prefill logprobs

* fix launcher

* fix logprobs?

* idk at this point

* max input length

* omfg

* remove debugging lines

* fix tests

* fix mllama

* fix cargo tests

* remove support chunking for paged

* Fixing non blocked attentions

* Fixing dtype + AMD, Ipex targets.

* lint fix.

* rename

* Fix prefix_caching variable, remove defaults in server (confusing a lot
of the times).

* Add simple resolution when user specifies ATTENTION=paged.

* Put back non default simple tests.

* Fix env name

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

* (feat) fp8 fnuz support for rocm

* (review comments) Fix compression_config load, type hints

* (bug) update all has_tensor

* (review_comments) fix typo and added comments

* (nit) improved comment

XPU backend is available natively (without IPEX) in pytorch starting
from pytorch 2.4. This commit extends TGI to cover the case when user
has XPU support thru pytorch 2.4, but does not have IPEX installed.
Models which don't require attention can work. For attention required
models more work is needed to provide attention implementation.

Tested with the following models:
* teknium/OpenHermes-2.5-Mistral-7B
* bigscience/bloom-560m
* google/gemma-7b
* google/flan-t5-xxl
Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com>

* Add support for fused MoE Marlin for AWQ

This uses the updated MoE Marlin kernels from vLLM.

* Add integration test for AWQ MoE

* Upgrade minor rust version (Fixes rust build compilation cache)

* Black

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

Update kv_cache.py

* Add basic FP8 KV cache support

This change adds rudimentary FP8 KV cache support. The support is
enabled by passing `--kv-cache-dtype fp8_e5m2` to the launcher. Doing so
uses this type for the KV cache. However support is still limited:

* Only the `fp8_e5m2` type is supported.
* The KV cache layout is the same as `float16`/`bfloat16` (HND).
* The FP8 KV cache is only supported for FlashInfer.
* Loading of scales is not yet supported.

* Fix Cargo.toml

* Working loading state.

* Preprocessing.

* Working state ? (Broke idefics1 temporarily).

* Cleaner condition.

* Fix idefics.

* Updating config, removing TODO

* Mllama

* Ugrade transformers 4.45

* Flashing mllama.

* Starting to get there.

* Working state.

* Integrations tests for mllama (cutting to 10 tokens because there seems'
to be instability after (meaning size of the batch matters.

* Updating model link.

* Earlier assert.

* Fix vlm ?

* remove log.

* Force ignore all images but last.

* Default dtype bfloat16.

* Update integration test after switch to bf16.

* Remove dead code.

* Removed dead code.

* Upgrade the flake to latest transformers/tokenizers

* Move to hf tgi-nix

* Upgrade to 0.5.0

This change uses the updated Marlin MoE kernel from vLLM to support
MoE with activation sorting and groups.

* feat: support phi3.5 moe model loading

* fix: prefer llama base model and improve rotary logic

* feat: return reasonable generation and add integration test

* fix: run lint and update docs

* fix: rerun lint for openapi docs

* fix: prefer do_sample false unless temp is set by user, and update chat tests

* fix: small typo adjustments

* fix: consolidate long rope paths

* fix: revert greedy by default and test changes

* Vendor configuration so that we don't have to `trust_remote_code`

* Use SparseMoELayer

* Add support for dense MoE

* Some type annotations

* Add the usual model tests

* Ruff.

---------
Co-authored-by: Daniël de Kok <me@danieldk.eu>
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>

This change add support for MoE models that use GPTQ quantization.
Currently only models with the following properties are supported:

- No `desc_act` with tensor parallelism, unless `group_size=-1`.
- No asymmetric quantization.
- No AWQ.

* style

* update torch

* ix issues

* fix clone

* revert mkl

* added custom PA

* style

* fix style

* style

* hide env vart

* fix mixtral model

* add skinny kernel and merge fixes

* fixed style

* fix issue for sliding window models

* addressed review comments

* fix import

* improved error messag

* updated default value

* remove import

* fix imports after rebase

* float16 dep

* improve dockerfile

* cleaned dockerfile

* Improve support for GPUs with capability < 8

- For models that cannot use flashinfer, use flash-attn v1 + paged
  attention for models with a compute capability older than 8.
- Disable prefix caching when using paged attention.
- When using flash-attn v1, pass the key/value, rather than the
  cache, since v1 cannot use block tables.

* nix: add flash-attn-v1 to the server environment

* Move disabling prefix caching into the block of exceptions

* Capability as `usize`s

* Add LoRA adapters support for Gemma2

* Make `black` formatting happy

* More tensor cores.

* Fixing the logic.

* Gemma is modified by this.

This replaces the custom layers in both models.

* Add support for scalar FP8 weight scales

* Support LLM compressor FP8 checkpoints on H100

On H100, we use fbgemm-gpu, which requires bfloat16 as the input dtype.
However, we wouldn't pick up fp8 quantization for models quantized with
LLM compressor. This change adds enough parsing to detect if models have
FP8-quantized weights.

* Remove stray debug print

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

* Move to moe-kernels package and switch to common MoE layer

This change introduces the new `moe-kernels` package:

- Add `moe-kernels` as a dependency.
- Introduce a `SparseMoELayer` module that can be used by MoE
  models.
- Port over Mixtral and Deepseek.

* Make `cargo check` pass

* Update runner

enable intel ipex cpu and xpu in python3.11
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

fix: pass missing revision arg for lora adapter when loading multiple adapters