hf_text-generation-inference/integration-tests/models/test_mamba.py

69 lines
2.0 KiB
Python
Raw Normal View History

Impl simple mamba model (#1480) This draft PR is a work in progress implementation of the mamba model. This PR currently loads weights, and produces correct logits after a single pass. This PR still needs to correctly integrate this model so it produces tokens as expected, and apply optimization to avoid all copies during runtime/unnecessary operations. #### Helpful resources [Mamba: Linear-Time Sequence Modeling with Selective State Spaces (Albert Gu and Tri Dao)](https://arxiv.org/abs/2312.00752) https://github.com/johnma2006/mamba-minimal https://github.com/huggingface/candle/blob/main/candle-examples/examples/mamba-minimal/model.rs https://github.com/huggingface/transformers/pull/28094 Notes: this dev work is currently targeting `state-spaces/mamba-130m`, so if you want to test please use that model. Additionally when starting the router the prefill needs to be limited: `cargo run -- --max-batch-prefill-tokens 768 --max-input-length 768` ## Update / Current State Integration tests have been added and basic functionality such as model loading is supported. ```bash cd integration-tests pytest -vv models/test_fused_kernel_mamba.py ``` - [x] add tests - [x] load model - [x] make simple request - [ ] resolve warmup issue - [ ] resolve output issues fetching models tested during dev ```bash text-generation-server download-weights state-spaces/mamba-130m text-generation-server download-weights state-spaces/mamba-1.4b text-generation-server download-weights state-spaces/mamba-2.8b ``` The server can be run ```bash cd server MASTER_ADDR=127.0.0.1 MASTER_PORT=5555 python text_generation_server/cli.py serve state-spaces/mamba-2.8b ``` router ```bash cargo run ``` make a request ```bash curl -s localhost:3000/generate \ -X POST \ -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":20}}' \ -H 'Content-Type: application/json' | jq ``` response ```json { "generated_text": "\n\nDeep learning is a machine learning technique that uses a deep neural network to learn from data." } ``` --------- Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-02-08 02:19:45 -07:00
import pytest
@pytest.fixture(scope="module")
def fused_kernel_mamba_handle(launcher):
with launcher("state-spaces/mamba-130m", num_shard=1) as handle:
yield handle
@pytest.fixture(scope="module")
async def fused_kernel_mamba(fused_kernel_mamba_handle):
await fused_kernel_mamba_handle.health(300)
return fused_kernel_mamba_handle.client
@pytest.mark.release
Impl simple mamba model (#1480) This draft PR is a work in progress implementation of the mamba model. This PR currently loads weights, and produces correct logits after a single pass. This PR still needs to correctly integrate this model so it produces tokens as expected, and apply optimization to avoid all copies during runtime/unnecessary operations. #### Helpful resources [Mamba: Linear-Time Sequence Modeling with Selective State Spaces (Albert Gu and Tri Dao)](https://arxiv.org/abs/2312.00752) https://github.com/johnma2006/mamba-minimal https://github.com/huggingface/candle/blob/main/candle-examples/examples/mamba-minimal/model.rs https://github.com/huggingface/transformers/pull/28094 Notes: this dev work is currently targeting `state-spaces/mamba-130m`, so if you want to test please use that model. Additionally when starting the router the prefill needs to be limited: `cargo run -- --max-batch-prefill-tokens 768 --max-input-length 768` ## Update / Current State Integration tests have been added and basic functionality such as model loading is supported. ```bash cd integration-tests pytest -vv models/test_fused_kernel_mamba.py ``` - [x] add tests - [x] load model - [x] make simple request - [ ] resolve warmup issue - [ ] resolve output issues fetching models tested during dev ```bash text-generation-server download-weights state-spaces/mamba-130m text-generation-server download-weights state-spaces/mamba-1.4b text-generation-server download-weights state-spaces/mamba-2.8b ``` The server can be run ```bash cd server MASTER_ADDR=127.0.0.1 MASTER_PORT=5555 python text_generation_server/cli.py serve state-spaces/mamba-2.8b ``` router ```bash cargo run ``` make a request ```bash curl -s localhost:3000/generate \ -X POST \ -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":20}}' \ -H 'Content-Type: application/json' | jq ``` response ```json { "generated_text": "\n\nDeep learning is a machine learning technique that uses a deep neural network to learn from data." } ``` --------- Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-02-08 02:19:45 -07:00
@pytest.mark.asyncio
async def test_mamba(fused_kernel_mamba, response_snapshot):
response = await fused_kernel_mamba.generate(
"What is Deep Learning?", max_new_tokens=10
)
assert response.details.generated_tokens == 10
assert response.generated_text == "\n\nDeep learning is a new type of machine"
assert response == response_snapshot
@pytest.mark.release
Impl simple mamba model (#1480) This draft PR is a work in progress implementation of the mamba model. This PR currently loads weights, and produces correct logits after a single pass. This PR still needs to correctly integrate this model so it produces tokens as expected, and apply optimization to avoid all copies during runtime/unnecessary operations. #### Helpful resources [Mamba: Linear-Time Sequence Modeling with Selective State Spaces (Albert Gu and Tri Dao)](https://arxiv.org/abs/2312.00752) https://github.com/johnma2006/mamba-minimal https://github.com/huggingface/candle/blob/main/candle-examples/examples/mamba-minimal/model.rs https://github.com/huggingface/transformers/pull/28094 Notes: this dev work is currently targeting `state-spaces/mamba-130m`, so if you want to test please use that model. Additionally when starting the router the prefill needs to be limited: `cargo run -- --max-batch-prefill-tokens 768 --max-input-length 768` ## Update / Current State Integration tests have been added and basic functionality such as model loading is supported. ```bash cd integration-tests pytest -vv models/test_fused_kernel_mamba.py ``` - [x] add tests - [x] load model - [x] make simple request - [ ] resolve warmup issue - [ ] resolve output issues fetching models tested during dev ```bash text-generation-server download-weights state-spaces/mamba-130m text-generation-server download-weights state-spaces/mamba-1.4b text-generation-server download-weights state-spaces/mamba-2.8b ``` The server can be run ```bash cd server MASTER_ADDR=127.0.0.1 MASTER_PORT=5555 python text_generation_server/cli.py serve state-spaces/mamba-2.8b ``` router ```bash cargo run ``` make a request ```bash curl -s localhost:3000/generate \ -X POST \ -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":20}}' \ -H 'Content-Type: application/json' | jq ``` response ```json { "generated_text": "\n\nDeep learning is a machine learning technique that uses a deep neural network to learn from data." } ``` --------- Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-02-08 02:19:45 -07:00
@pytest.mark.asyncio
async def test_mamba_all_params(fused_kernel_mamba, response_snapshot):
response = await fused_kernel_mamba.generate(
"blue, red, yellow, ",
max_new_tokens=10,
repetition_penalty=1.2,
return_full_text=True,
stop_sequences=["test"],
temperature=0.5,
top_p=0.9,
top_k=10,
truncate=5,
typical_p=0.9,
watermark=True,
decoder_input_details=True,
seed=0,
)
assert response.details.generated_tokens == 10
assert (
response.generated_text
Improving mamba runtime by using updates (#1552) - Move float16 to bfloat16, which has less imprecisions (load test are failing with the update kernels + f16, all working under bf16). Another note, is that we are not respecting the layer norm in f32 defined in the configuration (this is OK in my book, but that could impact the f16 precision) - Moved to update kernels. Triton overhead is super high, removed by switching to cuda graphs works great (update cuda graph is available in TRT-LLM if needed, seems *exactly* like the regular ssm kernel. - Moved inference_params struct in order to make only 2 tensors, to reduce the overhead of copying back and forth to the cuda graphs. - Left over overhead seems entirely in the tokenization bit. (Still 4 copies are paid before launching the graph) # What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflects the extent of your awesome contribution. Then, please replace this with a description of the change and which issue is fixed (if applicable). Please also include relevant motivation and context. List any dependencies (if any) that are required for this change. Once you're done, someone will review your PR shortly (see the section "Who can review?" below to tag some potential reviewers). They may suggest changes to make the code even better. If no one reviewed your PR after a week has passed, don't hesitate to post a new comment @-mentioning the same persons---sometimes notifications get lost. --> <!-- Remove if not applicable --> Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. <!-- Your PR will be replied to more quickly if you can figure out the right person to tag with @ @OlivierDehaene OR @Narsil -->
2024-02-14 01:54:10 -07:00
== "blue, red, yellow, \nand blue colors. A number of different color"
)
Impl simple mamba model (#1480) This draft PR is a work in progress implementation of the mamba model. This PR currently loads weights, and produces correct logits after a single pass. This PR still needs to correctly integrate this model so it produces tokens as expected, and apply optimization to avoid all copies during runtime/unnecessary operations. #### Helpful resources [Mamba: Linear-Time Sequence Modeling with Selective State Spaces (Albert Gu and Tri Dao)](https://arxiv.org/abs/2312.00752) https://github.com/johnma2006/mamba-minimal https://github.com/huggingface/candle/blob/main/candle-examples/examples/mamba-minimal/model.rs https://github.com/huggingface/transformers/pull/28094 Notes: this dev work is currently targeting `state-spaces/mamba-130m`, so if you want to test please use that model. Additionally when starting the router the prefill needs to be limited: `cargo run -- --max-batch-prefill-tokens 768 --max-input-length 768` ## Update / Current State Integration tests have been added and basic functionality such as model loading is supported. ```bash cd integration-tests pytest -vv models/test_fused_kernel_mamba.py ``` - [x] add tests - [x] load model - [x] make simple request - [ ] resolve warmup issue - [ ] resolve output issues fetching models tested during dev ```bash text-generation-server download-weights state-spaces/mamba-130m text-generation-server download-weights state-spaces/mamba-1.4b text-generation-server download-weights state-spaces/mamba-2.8b ``` The server can be run ```bash cd server MASTER_ADDR=127.0.0.1 MASTER_PORT=5555 python text_generation_server/cli.py serve state-spaces/mamba-2.8b ``` router ```bash cargo run ``` make a request ```bash curl -s localhost:3000/generate \ -X POST \ -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":20}}' \ -H 'Content-Type: application/json' | jq ``` response ```json { "generated_text": "\n\nDeep learning is a machine learning technique that uses a deep neural network to learn from data." } ``` --------- Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-02-08 02:19:45 -07:00
assert response == response_snapshot
@pytest.mark.release
Impl simple mamba model (#1480) This draft PR is a work in progress implementation of the mamba model. This PR currently loads weights, and produces correct logits after a single pass. This PR still needs to correctly integrate this model so it produces tokens as expected, and apply optimization to avoid all copies during runtime/unnecessary operations. #### Helpful resources [Mamba: Linear-Time Sequence Modeling with Selective State Spaces (Albert Gu and Tri Dao)](https://arxiv.org/abs/2312.00752) https://github.com/johnma2006/mamba-minimal https://github.com/huggingface/candle/blob/main/candle-examples/examples/mamba-minimal/model.rs https://github.com/huggingface/transformers/pull/28094 Notes: this dev work is currently targeting `state-spaces/mamba-130m`, so if you want to test please use that model. Additionally when starting the router the prefill needs to be limited: `cargo run -- --max-batch-prefill-tokens 768 --max-input-length 768` ## Update / Current State Integration tests have been added and basic functionality such as model loading is supported. ```bash cd integration-tests pytest -vv models/test_fused_kernel_mamba.py ``` - [x] add tests - [x] load model - [x] make simple request - [ ] resolve warmup issue - [ ] resolve output issues fetching models tested during dev ```bash text-generation-server download-weights state-spaces/mamba-130m text-generation-server download-weights state-spaces/mamba-1.4b text-generation-server download-weights state-spaces/mamba-2.8b ``` The server can be run ```bash cd server MASTER_ADDR=127.0.0.1 MASTER_PORT=5555 python text_generation_server/cli.py serve state-spaces/mamba-2.8b ``` router ```bash cargo run ``` make a request ```bash curl -s localhost:3000/generate \ -X POST \ -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":20}}' \ -H 'Content-Type: application/json' | jq ``` response ```json { "generated_text": "\n\nDeep learning is a machine learning technique that uses a deep neural network to learn from data." } ``` --------- Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-02-08 02:19:45 -07:00
@pytest.mark.asyncio
2024-02-16 03:58:58 -07:00
async def test_mamba_load(
fused_kernel_mamba, generate_load, generous_response_snapshot
):
responses = await generate_load(
fused_kernel_mamba, "What is Deep Learning?", max_new_tokens=10, n=4
)
Impl simple mamba model (#1480) This draft PR is a work in progress implementation of the mamba model. This PR currently loads weights, and produces correct logits after a single pass. This PR still needs to correctly integrate this model so it produces tokens as expected, and apply optimization to avoid all copies during runtime/unnecessary operations. #### Helpful resources [Mamba: Linear-Time Sequence Modeling with Selective State Spaces (Albert Gu and Tri Dao)](https://arxiv.org/abs/2312.00752) https://github.com/johnma2006/mamba-minimal https://github.com/huggingface/candle/blob/main/candle-examples/examples/mamba-minimal/model.rs https://github.com/huggingface/transformers/pull/28094 Notes: this dev work is currently targeting `state-spaces/mamba-130m`, so if you want to test please use that model. Additionally when starting the router the prefill needs to be limited: `cargo run -- --max-batch-prefill-tokens 768 --max-input-length 768` ## Update / Current State Integration tests have been added and basic functionality such as model loading is supported. ```bash cd integration-tests pytest -vv models/test_fused_kernel_mamba.py ``` - [x] add tests - [x] load model - [x] make simple request - [ ] resolve warmup issue - [ ] resolve output issues fetching models tested during dev ```bash text-generation-server download-weights state-spaces/mamba-130m text-generation-server download-weights state-spaces/mamba-1.4b text-generation-server download-weights state-spaces/mamba-2.8b ``` The server can be run ```bash cd server MASTER_ADDR=127.0.0.1 MASTER_PORT=5555 python text_generation_server/cli.py serve state-spaces/mamba-2.8b ``` router ```bash cargo run ``` make a request ```bash curl -s localhost:3000/generate \ -X POST \ -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":20}}' \ -H 'Content-Type: application/json' | jq ``` response ```json { "generated_text": "\n\nDeep learning is a machine learning technique that uses a deep neural network to learn from data." } ``` --------- Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2024-02-08 02:19:45 -07:00
assert len(responses) == 4
assert all([r.generated_text == responses[0].generated_text for r in responses])
assert responses[0].generated_text == "\n\nDeep learning is a new type of machine"
Improving mamba runtime by using updates (#1552) - Move float16 to bfloat16, which has less imprecisions (load test are failing with the update kernels + f16, all working under bf16). Another note, is that we are not respecting the layer norm in f32 defined in the configuration (this is OK in my book, but that could impact the f16 precision) - Moved to update kernels. Triton overhead is super high, removed by switching to cuda graphs works great (update cuda graph is available in TRT-LLM if needed, seems *exactly* like the regular ssm kernel. - Moved inference_params struct in order to make only 2 tensors, to reduce the overhead of copying back and forth to the cuda graphs. - Left over overhead seems entirely in the tokenization bit. (Still 4 copies are paid before launching the graph) # What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflects the extent of your awesome contribution. Then, please replace this with a description of the change and which issue is fixed (if applicable). Please also include relevant motivation and context. List any dependencies (if any) that are required for this change. Once you're done, someone will review your PR shortly (see the section "Who can review?" below to tag some potential reviewers). They may suggest changes to make the code even better. If no one reviewed your PR after a week has passed, don't hesitate to post a new comment @-mentioning the same persons---sometimes notifications get lost. --> <!-- Remove if not applicable --> Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. <!-- Your PR will be replied to more quickly if you can figure out the right person to tag with @ @OlivierDehaene OR @Narsil -->
2024-02-14 01:54:10 -07:00
assert responses == generous_response_snapshot