Commit Graph

104 Commits

Author SHA1 Message Date
Morgan Funtowicz 612f2f939f feat(backend): bind incoming request to the server 2024-11-14 08:42:01 +01:00
Morgan Funtowicz d4aee42fd8 feat(backend): add logit parameter in the callback fn 2024-11-14 08:42:01 +01:00
Morgan Funtowicz f39edc72ff feat(backend): add mapping for ignore_eos_token stopping criteria 2024-11-14 08:42:01 +01:00
Morgan Funtowicz 3af2c6837c misc(offline): match rework 2024-11-14 08:42:01 +01:00
Morgan Funtowicz d52b4c4978 feat(backend): full rework of the backend internal to safer c++ 2024-11-14 08:42:01 +01:00
Morgan Funtowicz 6a5f6b0755 misc(offline): update offline tester 2024-11-14 08:42:01 +01:00
Morgan Funtowicz b98c635781 feat(backend): entirely rewrite backend 2024-11-14 08:42:01 +01:00
Morgan Funtowicz 611590440d misc(offline): expose more parameters for generate 2024-11-14 08:42:01 +01:00
Morgan Funtowicz dbc5b7a0f7 misc(offline): link correctly 2024-11-14 08:42:01 +01:00
Morgan Funtowicz 0c1dd0ed2b feat(llamacpp): wip explosion 2024-11-14 08:42:01 +01:00
Morgan Funtowicz a316c53255 feat(llamacpp): expose number of threads for the backend when constructing the model 2024-11-14 08:42:01 +01:00
Morgan Funtowicz 179309b364 misc(build): refactor build type detection in cmake 2024-11-14 08:42:01 +01:00
Morgan Funtowicz f0859c247f misc(build): handle different lib destination folder lib/lib64 2024-11-14 08:42:01 +01:00
Morgan Funtowicz e4d803c94e feat(backend): build and link through build.rs 2024-11-14 08:42:01 +01:00
Morgan Funtowicz 355d8a55b4 feat(backend): wip Rust binding 2024-11-14 08:42:01 +01:00
Morgan Funtowicz f9c248657d chore(backend): minor formatting 2024-11-14 08:42:01 +01:00
Morgan Funtowicz 37faeb34b2 feat(backend): expose frequency and repetition penalties 2024-11-14 08:42:01 +01:00
Morgan Funtowicz d4b5be10f9 feat(backend): minor refactor 2024-11-14 08:42:01 +01:00
Morgan Funtowicz 92bb113653 feat(backend): use llama_token as TokenId type 2024-11-14 08:42:01 +01:00
Morgan Funtowicz 45d5a6a8c5 feat(backend): add some initial decoding steps 2024-11-14 08:42:01 +01:00
Morgan Funtowicz 098c66920d feat(backend): tell cmake to build llama-common and link to it 2024-11-14 08:42:01 +01:00
Morgan Funtowicz 0911076320 feat(backend): correctly load llama.cpp model from llama api and not gpt2 2024-11-14 08:42:01 +01:00
Morgan Funtowicz 05ad684676 feat(llamacpp): enable cuda 2024-11-14 08:42:01 +01:00
Morgan Funtowicz fa89d1e613 misc(cmake): wut 2024-11-14 08:42:01 +01:00
Morgan Funtowicz e4432d36b1 misc(cmake): add parameter to build specific cuda arch 2024-11-14 08:42:01 +01:00
Morgan Funtowicz 52d57dca79 feat(llamacpp): initial end2end build 2024-11-14 08:42:01 +01:00
Morgan Funtowicz 7d1f8a2bd6 feat(llamacpp): correctly handle CMAKE_BUILD_TYPE for spdlog macros 2024-11-14 08:42:01 +01:00
Morgan Funtowicz aa1fcba59f feat(llamacpp): initial commit
# Conflicts:
#	Cargo.lock
2024-11-14 08:42:01 +01:00
Nicolas Patry 0c9b6cdd76
Choosing input/total tokens automatically based on available VRAM? (#2673)
* 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).
2024-10-28 04:59:49 +01:00
Funtowicz Morgan ba5fc7d922
Add support for stop words in TRTLLM (#2678)
* feat(trtllm): rewrite health to not account for current state

* chore(looper): cleanup a bit more

* feat(post_processing): max_new_tokens is const evaluated now

* chore(ffi):formatting

* feat(trtllm): add stop words handling

# Conflicts:
#	backends/trtllm/lib/backend.cpp

* chore(trtllm): create specific parallelconfig factory and logging init methods

* chore(trtllm): define a macro for SizeType cast

* chore(trtllm): use GetParallelConfig

* chore(trtllm): minor refactoring

* chore(trtllm): validate there are enough GPus on the system for the desired model

* chore(trtllm): ensure max throughput scheduling policy is selected

* chore(trtllm): minor fix

* chore(router): minor refactorings

* feat(docker): build with-slurm ompi

* feat(docker): add python3.10 dev to runtime deps

* chore(docker): add mpi to ld_library_path

* chore(docker): install transformers

* feat(trtllm): detect stop_words from generation_config.json
2024-10-25 10:58:34 +02:00
Funtowicz Morgan 43df056eee
[TENSORRT-LLM] - Implement new looper thread based backend (#2357)
* (backend) use parking_lot crate for RwLock fairness

# Conflicts:
#	backends/trtllm/src/backend.rs

* (launcher) default new server::run parameters to false for now

* (chore) fmt ... why?

* (ffi) use const for GetSamplingConfig

* (server) expose new SchedulingError

* (trt)

* (build) setup ccache if available

* (ffi) add max_new_tokens parameters

* (backend) cleanup a bit

* (backend) expose PullNewTokens

* (ffi) cleanup again

* (ffi) add missing headers imports

* (ffi) add template specialization to catch and convert to Rust Result<T, tensorrt_llm::common::TllmException>

* (looper) new looper initial implementation

* (ffi) remove narrowing type warning

* (ffi) encode the provided user prompt within each request thread

* (misc) change scope identifiers

* (backend) implement the post_processor background thread

* (misc) missing Result types for Rust

* use blocking_recv in looper to consume awaiting_requests at max before pulling in a single step

* (server) forward auth_token to server::run

* (build) fetchcontent use archives instead of git

* (ffi) fix usage of wrong vector constructor making a capacity fill call

* (ffi) missing namespace for tle::Response

* (ffi) do not use reference capture in lambda as we are not capturing anything

* (backend) refactor & cleanup

* (Dockerfile.trtllm) delete for now

* (misc) simplify [make_]move_iterator by using c++20 type inference

* (misc) no need to move for uint32_t items

* (scheduler) rework submit/pull logic

* (post) impl postprocessing

* (misc) delete backend.rs

* (misc) rerun-if-changed all the cmake modules

* (misc) move to latest trtllm

* (fix): HOPPER_SM_MAJOR is 9 not 8

* (misc: build for sm_{75,80,86,89,90} by default

* (misc): build with trtllm 0.13.0

* (misc): increase verbosity of spdlog

* (fix): do not recreate the stateful hashmap at every it

* (misc): update dependency in trtllm dockerfile

* (misc): update dependency in trtllm dockerfile

* (misc): disable logging in release mode

* (misc): improve trtllm download script robustness

* (fix): ore fixes for Dockerfile

* misc(cuda): require 12.6

* chore(cmake): use correct policy for download_timestamp

* feat(looper): check engine and executorWorker paths exist before creating the backend

* chore(cmake): download timestamp should be before URL

* feat(looper): minor optimizations to avoid growing too much the containers

* chore(trtllm): move dockerfile to right place

* chore(trtllm): disable tokenizer parallelism by default

* chore(trtllm): fmt

* chore(trtllm): post-rebase commit

* chore(trtllm): remove unused method

* feat(trtllm): cache maxNumTokens to avoid calling JSON everytime

* misc(router): remove SchedulingError

* feat(trtllm): do not tokenize twice

* Revert "chore(trtllm): remove unused method"

This reverts commit 31747163

* chore(rebase): fix invalid references

* chore(router): add python dependency

* Lint.

* Fix bad rebase

---------

Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-10-25 07:17:14 +02:00
Nicolas Patry ed87b464b4
Fixing "deadlock" when python prompts for trust_remote_code by always (#2664)
specifiying a value.
2024-10-25 06:39:21 +02:00
OlivierDehaene 41c2623735
feat: allow any supported payload on /invocations (#2683)
* feat: allow any supported payload on /invocations

* update openAPI

* update doc
2024-10-23 11:26:01 +00:00
OlivierDehaene a6a0c97ed9
feat: prefill chunking (#2600)
* 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>
2024-10-16 12:49:33 +02:00
Nicolas Patry 0204946d26
Max token capacity metric (#2595)
* adding max_token_capacity_metric

* added tgi to name of metric

* Adding max capacity metric.

* Add description for the metrics

---------

Co-authored-by: Edwinhr716 <Edandres249@gmail.com>
2024-10-02 16:32:36 +02:00
Nicolas Patry 0ff6ff60ad
Hotfixing main (#2556) 2024-09-24 11:51:14 +02:00
OlivierDehaene 10e6f29295
chore: Add old V2 backend (#2551)
* wip

* added v2
2024-09-24 08:38:17 +02:00
Nicolas Patry 38fcafcf96
Adding a test for FD. (#2516)
* Adding a test for FD.

* Fixing flashdecoding (empty batch doesn't work).

* Fixing the invalid popping.

* Fixing radix with block_size > 1

* Last reference.

* Use an actual hash.

* Update hash for slice.len() == 1

* Update the locks.

* Increasing docker timeout.
2024-09-16 17:00:54 +02:00
Nicolas Patry dae3bf1d87
Fix tokenization yi (#2507)
* Fixing odd tokenization self modifications on the Rust side (load and
resave in Python).

* Fixing the builds ?

* Fix the gh action?

* Fixing the location ?

* Validation is odd.

* Try a faster runner

* Upgrade python version.

* Remove sccache

* No sccache.

* Getting libpython maybe ?

* List stuff.

* Monkey it up.

* have no idea at this point

* Tmp.

* Shot in the dark.

* Tmate the hell out of this.

* Desperation.

* WTF.

* -y.

* Apparently 3.10 is not available anymore.

* Updating the dockerfile to make libpython discoverable at runtime too.

* Put back rust tests.

* Why do we want mkl on AMD ?

* Forcing 3.11 ?
2024-09-11 22:41:56 +02:00
Nicolas Patry a4e3e8c608
Prefix test - Different kind of load test to trigger prefix test bugs. (#2490)
* Adding prefix test.

* [WIP] tmp dump of integration load tests.

* Remove other tensor creation.

* Fixed the radix tree.

Used a slice everywhere in radix.rs to keep the cheap Arc cloning
instead of recomputing the input_ids.

* Fix parsing

* Is it really flashinfer version ?

* Remove some comments.

* Revert the max prefix hit.

* Adding numpy to diff.

* Upgraded flashinfer.

* Upgrading some stuff.

* Are we done yet ?

* Minor fixup

* Remove 1 log and put back the other.

* Add comment for why slot 0 is OK.

* Mounting on the job.

* Get me a debug branch

* Debugging CIs is fun.

* Attempt #28

* wip

* Tmate.

* Praying.

* Updating VLM causal model with updated context.

* Important line got squashed.

* Tmate again.

* Fingers crossed.

* We want only 1 run of integration tests.....

---------

Co-authored-by: Guillaume LEGENDRE <glegendre01@gmail.com>
2024-09-11 18:10:40 +02:00
Nicolas Patry c1fe28d694
Fixing more correctly the invalid drop of the batch. (#2498) 2024-09-06 17:35:49 +02:00
Daniël de Kok 379472c4c2
radix trie: add assertions (#2491)
These should all be cheap assertions.

Also:

* Fixup some comments.
* Delete a `remove` that was done unnecessarily twice.
2024-09-06 11:55:23 +02:00
Daniël de Kok deec30f893
hotfix: avoid non-prefilled block use when using prefix caching (#2489)
The minimum batch size logic could cause prefix blocks to be
deallocated without prefill. The next allocation of the same
prefix would then use garbage blocks.
2024-09-05 15:09:29 +02:00
Nicolas Patry e415b690a6
Lots of improvements (Still 2 allocators) (#2449)
* Making prefix/flashinfer the default and testing the full release tests.

* Include flashinfer in the docker.

* Using prebuilt.

* Allowing window_left_size (dummy version).

* Disabling flashinfer/prefix caching on odd head_dim

* Disable prefix caching for lora.

* More specific codes.

* Update lock

* Updating integration tests with new values with FI/FD.

Remove paged as a default too, and using FD everywhere.

* Update cargo lock ?

* Upgrade to 1.80 because of bitstream...

* Everywhere 1.80

* Forgot last default place.

* Apply suggestions from code review

Co-authored-by: drbh <david.richard.holtz@gmail.com>

* Updated flake lock

* Tmp

* Upgrade resolution system for less errors in resolution.

* Remove lambda for cleaner function.

* Handling debugger.

* OVerride the env in server tests.

* Is this enough to make it work ?

* This seems to be working.

* Downgrade some logs.

* Fixing the default for vlm.

* Don't enable prefix caching on VLM just yet.

* Change `add_special_tokens` in order to have the correct tokens for chat
input and not (since it's super important with the prefixing now)

* Fixing prefix caching for flashdecoding.

* Update all models.

* Fixed flashinfer version.

* add_special_tokens is internal only

* Fixing seqlen with the new vlms.

* Fixing the issue with `add_special_tokens` not being passed around.

* Fixing the test.

* Removing encoder_decoder (seq2seq).

* Update the chat test.

* Fixing the batching tokenization in flash causal lm.

* Truncating left for radix purposes.

* Oops this doesn't belong here.

* Put back default pure shell.

* Update server tests

- Default to throughput test in k6
- Use TGI_WIGGLE_ROOM to adjust wiggle room

* Only n_heads / process_group.size() are necessary.

* Revert the integrationt tests change (seem linked to head_size
modification).

* Adding error message when assert is violated.

* Fixing the free algorithm to handle times where the common prefix is
smaller.

* Apply suggestions from code review

Co-authored-by: OlivierDehaene <olivier@huggingface.co>

* Update server/text_generation_server/layers/attention/common.py

Co-authored-by: OlivierDehaene <olivier@huggingface.co>

* Fix disabling prefix caching - Fix windowing checks.

* Revert the Cohere tokenizer change (for now using a revision instead).

* Fmt.

---------

Co-authored-by: drbh <david.richard.holtz@gmail.com>
Co-authored-by: OlivierDehaene <olivier@huggingface.co>
2024-08-29 16:29:01 +02:00
drbh 21187c27c9
fix: bump minijinja version and add test for llama 3.1 tools (#2463)
* fix: support tojson and avoid message indexing issue in template

* fix: prefer minijinja native methods and prefer workspace level dependency

* fix: adjust comment typo
2024-08-27 13:31:08 -04:00
Nicolas Patry b70ae0969f
Prefix caching (#2402)
* 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>
2024-08-20 11:15:30 +02:00
Funtowicz Morgan 3f385991b0
More fixes trtllm (#2342)
* (backend) use parking_lot crate for RwLock fairness

* (docker) let's put rust in the TRTLLM folder when building

* (docker) build ompi with SLURM support

* (launcher) default new server::run parameters to false for now

* (chore) fmt ... why?
2024-08-14 12:02:05 +02:00
Nicolas Patry 136bcc8128
Keeping the benchmark somewhere (#2401)
Co-authored-by: Daniël de Kok <me@danieldk.eu>
2024-08-12 15:22:02 +02:00
Daniël de Kok 8deeaca4ff
Add support for prefix caching to the v3 router (#2392)
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.
2024-08-12 14:59:17 +02:00
Nicolas Patry 7a48a84784
Using an enum for flash backens (paged/flashdecoding/flashinfer) (#2385)
* Using an enum for flash backens (paged/flashdecoding/flashinfer)

* Early exit on server too.

* Clippy.

* Fix clippy and fmt.
2024-08-09 16:41:17 +02:00
drbh 6d06473cf4
Pr 2352 ci branch (#2382)
* Fix unsigned integer underflow

Passing --max-batch-size to the launcher actually had no effect
because after a few requests the max_size passed to State::next_batch
would underflow becoming a largo positive number.

In the scheduler, as soon as the cached batch size reached the
max_batch_size the max_size passed to next_batch becomes 0.
Since the only check in that funcion is
```
if Some(batch_requests.len()) == max_size {
    break;
}
```
and it's called after the `batch_requests.len()` has
become 1, it doesn't do anything to prevent more than 0
requests from being batched.

Now we have cached batch in the server that is large than
max_batch_size and `max_size - batch_size as usize`
underflows.

Signed-off-by: Max de Bayser <mbayser@br.ibm.com>

* fix: update v3 scheduler and ensure max_batch_size > 0

---------

Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Max de Bayser <mbayser@br.ibm.com>
2024-08-09 10:54:32 +02:00
Daniël de Kok 22fb1be588
Fix cache block size for flash decoding (#2351)
* Fix cache block size for flash decoding

This seems to have been accidentally dropped during the TRT-LLM
PR rebase.

* Also run CI on changes to `backends`
2024-08-01 15:38:57 +02:00
Erik Kaunismäki 7451041ecd
refactor usage stats (#2339)
* refactor usage stats

* Update docs/source/usage_statistics.md

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

* Update router/src/server.rs

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

* changes based on feedback

* run python3 udpate_doc.py

* fix pre-commit

* Update router/src/server.rs

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

* delete option around usage stats arg

---------

Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-07-31 16:29:07 +02:00
Nicolas Patry 2b19d671b4
Rebase TRT-llm (#2331)
* wip

wip

refacto

refacto

Initial setup for CXX binding to TRTLLM

Working FFI call for TGI and TRTLLM backend

Remove unused parameters annd force tokenizer name to be set

Overall build TRTLLM and deps through CMake build system

Enable end to end CMake build

First version loading engines and making it ready for inference

Remembering to check how we can detect support for chunked context

Move to latest TensorRT-LLM version

Specify which default log level to use depending on CMake build type

make leader executor mode working

unconditionally call InitializeBackend on the FFI layer

bind to CUDA::nvml to retrieve compute capabilities at runtime

updated logic and comment to detect cuda compute capabilities

implement the Stream method to send new tokens through a callback

use spdlog release 1.14.1 moving forward

update trtllm to latest version a96cccafcf6365c128f004f779160951f8c0801c

correctly tell cmake to build dependent tensorrt-llm required libraries

create cmake install target to put everything relevant in installation folder

add auth_token CLI argument to provide hf hub authentification token

allow converting huggingface::tokenizers error to TensorRtLlmBackendError

use correct include for spdlog

include guard to build example in cmakelists

working setup of the ffi layer

remove fmt import

use external fmt lib

end to end ffi flow working

make sure to track include/ffi.h to trigger rebuild from cargo

impl the rust backend which currently cannot move the actual computation in background thread

expose shutdown function at ffi layer

impl RwLock scenario for TensorRtLllmBackend

oops missing c++ backend definitions

compute the number of maximum new tokens for each request independently

make sure the context is not dropped in the middle of the async decoding.

remove unnecessary log

add all the necessary plumbery to return the generated content

update invalid doc in cpp file

correctly forward back the log probabilities

remove unneeded scope variable for now

refactor Stream impl for Generation to factorise code

expose the internal missing start/queue timestamp

forward tgi parameters rep/freq penalty

add some more validation about grammar not supported

define a shared struct to hold the result of a decoding step

expose information about potential error happening while decoding

remove logging

add logging in case of decoding error

make sure executor_worker is provided

add initial Dockerfile for TRTLLM backend

add some more information in CMakeLists.txt to correctly install executorWorker

add some more information in CMakeLists.txt to correctly find and install nvrtc wrapper

simplify prebuilt trtllm libraries name definition

do the same name definition stuff for tensorrt_llm_executor_static

leverage pkg-config to probe libraries paths and reuse new install structure from cmake

fix bad copy/past missing nvinfer linkage direction

align all the linker search dependency

add missing pkgconfig folder for MPI in Dockerfile

correctly setup linking search path for runtime layer

fix missing / before tgi lib path

adding missing ld_library_path for cuda stubs in Dockerfile

update tgi entrypoint

commenting out Python part for TensorRT installation

refactored docker image

move to TensorRT-LLM v0.11.0

make docker linter happy with same capitalization rule

fix typo

refactor the compute capabilities detection along with num gpus

update TensorRT-LLM to latest version

update TensorRT install script to latest

update build.rs to link to cuda 12.5

add missing dependant libraries for linking

clean up a bit

install to decoder_attention target

add some custom stuff for nccl linkage

fix envvar CARGO_CFG_TARGET_ARCH set at runtime vs compile time

use std::env::const::ARCH

make sure variable live long enough...

look for cuda 12.5

add some more basic info in README.md

* Rebase.

* Fix autodocs.

* Let's try to enable trtllm backend.

* Ignore backends/v3 by default.

* Fixing client.

* Fix makefile + autodocs.

* Updating the schema thing + redocly.

* Fix trtllm lint.

* Adding pb files ?

* Remove cargo fmt temporarily.

* ?

* Tmp.

* Remove both check + clippy  ?

* Backporting telemetry.

* Backporting 457fb0a1

* Remove PB from git.

* Fixing PB with default member backends/client

* update TensorRT-LLM to latest version

* provided None for api_key

* link against libtensorrt_llm and not libtensorrt-llm

---------

Co-authored-by: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com>
Co-authored-by: Morgan Funtowicz <morgan@huggingface.co>
2024-07-31 10:33:10 +02:00