Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add qwen config and and input config simplification #1190

Open
wants to merge 10 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion pyproject.toml
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
[tool.poetry]
name = "truss"
version = "0.9.44"
version = "0.9.45rc006"
description = "A seamless bridge from model development to model delivery"
license = "MIT"
readme = "README.md"
Expand Down
9 changes: 4 additions & 5 deletions truss/config/trt_llm.py
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ class TrussTRTLLMModel(str, Enum):
MISTRAL = "mistral"
DEEPSEEK = "deepseek"
WHISPER = "whisper"
QWEN = "qwen"


class TrussTRTLLMQuantizationType(str, Enum):
Expand Down Expand Up @@ -58,10 +59,9 @@ class CheckpointRepository(BaseModel):

class TrussTRTLLMBuildConfiguration(BaseModel):
base_model: TrussTRTLLMModel
max_input_len: int
max_output_len: int
max_batch_size: int
max_num_tokens: Optional[int] = None
max_seq_len: int
max_batch_size: Optional[int] = 256
max_num_tokens: Optional[int] = 8192
max_beam_width: int = 1
max_prompt_embedding_table_size: int = 0
checkpoint_repository: CheckpointRepository
Expand All @@ -75,7 +75,6 @@ class TrussTRTLLMBuildConfiguration(BaseModel):
plugin_configuration: TrussTRTLLMPluginConfiguration = (
TrussTRTLLMPluginConfiguration()
)
use_fused_mlp: bool = False
Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

moved to plugin config – defaulted to true

kv_cache_free_gpu_mem_fraction: float = 0.9
num_builder_gpus: Optional[int] = None
enable_chunked_context: bool = False
Expand Down
2 changes: 1 addition & 1 deletion truss/constants.py
Original file line number Diff line number Diff line change
Expand Up @@ -106,7 +106,7 @@

REGISTRY_BUILD_SECRET_PREFIX = "DOCKER_REGISTRY_"

TRTLLM_BASE_IMAGE = "baseten/briton-server:5fa9436e_v0.0.11"
TRTLLM_BASE_IMAGE = "baseten/briton-server:v0.13.0"
TRTLLM_PYTHON_EXECUTABLE = "/usr/bin/python3"
BASE_TRTLLM_REQUIREMENTS = [
"grpcio==1.62.3",
Expand Down
3 changes: 1 addition & 2 deletions truss/test_data/test_trt_llm_truss/config.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -4,10 +4,9 @@ resources:
use_gpu: True
trt_llm:
build:
max_input_len: 1000
max_seq_len: 1000
max_batch_size: 1
max_beam_width: 1
max_output_len: 1000
base_model: llama
checkpoint_repository:
repo: TinyLlama/TinyLlama-1.1B-Chat-v1.0
Expand Down
3 changes: 1 addition & 2 deletions truss/tests/conftest.py
Original file line number Diff line number Diff line change
Expand Up @@ -389,8 +389,7 @@ def modify_handle(h: TrussHandle):
content["trt_llm"] = {
"build": {
"base_model": "llama",
"max_input_len": 1024,
"max_output_len": 1024,
"max_seq_len": 2048,
"max_batch_size": 512,
"checkpoint_repository": {
"source": "HF",
Expand Down
3 changes: 1 addition & 2 deletions truss/tests/test_config.py
Original file line number Diff line number Diff line change
Expand Up @@ -52,8 +52,7 @@ def trtllm_config(default_config) -> Dict[str, Any]:
trtllm_config["trt_llm"] = {
"build": {
"base_model": "llama",
"max_input_len": 1024,
"max_output_len": 1024,
"max_seq_len": 2048,
"max_batch_size": 512,
"checkpoint_repository": {
"source": "HF",
Expand Down
Loading