Skip to main content

Fast and easy LLM serving.

Project description

mistral.rs

mistralrs is a Python package which provides an easy to use API for mistral.rs.

Example

More examples can be found here!

from mistralrs import Runner, Which, ChatCompletionRequest

runner = Runner(
    which=Which.Plain(
        model_id="microsoft/Phi-3.5-mini-instruct",
    ),
    in_situ_quant="Q4K",
)

res = runner.send_chat_completion_request(
    ChatCompletionRequest(
        model="mistral",
        messages=[
            {"role": "user", "content": "Tell me a story about the Rust type system."}
        ],
        max_tokens=256,
        presence_penalty=1.0,
        top_p=0.1,
        temperature=0.1,
    )
)
print(res.choices[0].message.content)
print(res.usage)

Please find API docs here and the type stubs here, which are another great form of documentation.

We also provide a cookbook here!

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

mistralrs_cuda-0.3.2-cp312-cp312-manylinux_2_34_x86_64.whl (23.5 MB view details)

Uploaded CPython 3.12 manylinux: glibc 2.34+ x86-64

mistralrs_cuda-0.3.2-cp311-cp311-manylinux_2_34_x86_64.whl (23.5 MB view details)

Uploaded CPython 3.11 manylinux: glibc 2.34+ x86-64

mistralrs_cuda-0.3.2-cp310-cp310-manylinux_2_34_x86_64.whl (23.5 MB view details)

Uploaded CPython 3.10 manylinux: glibc 2.34+ x86-64

File details

Details for the file mistralrs_cuda-0.3.2-cp312-cp312-manylinux_2_34_x86_64.whl.

File metadata

File hashes

Hashes for mistralrs_cuda-0.3.2-cp312-cp312-manylinux_2_34_x86_64.whl
Algorithm Hash digest
SHA256 cb3afff5c1cb4840222149d4285cae252a12b15c8c26fa8d0b533d4077b96c29
MD5 cfa9ce22bb5a2ee7edd3da54f31e9454
BLAKE2b-256 35415230a8e6fd59db62deee672b4cbe5377e9fd9d4e78f46b8130d3f943027a

See more details on using hashes here.

File details

Details for the file mistralrs_cuda-0.3.2-cp311-cp311-manylinux_2_34_x86_64.whl.

File metadata

File hashes

Hashes for mistralrs_cuda-0.3.2-cp311-cp311-manylinux_2_34_x86_64.whl
Algorithm Hash digest
SHA256 1fbf2d1391082769a0ee433d826d3133174e629f5df73f34eb8aba99f641db1c
MD5 61e3d7e5c2a68f2fa7b522315a8ab20f
BLAKE2b-256 21802efae216147467018672e660426ca7c918c1c37626fbdfb0425b46a9709b

See more details on using hashes here.

File details

Details for the file mistralrs_cuda-0.3.2-cp310-cp310-manylinux_2_34_x86_64.whl.

File metadata

File hashes

Hashes for mistralrs_cuda-0.3.2-cp310-cp310-manylinux_2_34_x86_64.whl
Algorithm Hash digest
SHA256 e5fc53994702e7a9be3339ac6dfd133608b05b0e6133a6702ad9d3e6934c24c4
MD5 524c4331b9172f543f9d19836f9ffca0
BLAKE2b-256 3a5d6902f12c9ce24d8848711a73cc7c41926a0d51c48f91d46fc6dcdebc33de

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page