Commit Graph

8 Commits

Author SHA1 Message Date
Daniël de Kok
036d802b62
Nix: add openai to impure shell for integration tests (#3081) 2025-03-07 13:04:21 +01:00
Daniël de Kok
571ac9b507
Use kernels from the kernel hub (#2988)
* Use Hub kernels for Marlin and cutlass quantization kernels

* Use hub kernels for MoE/GPTQ-Marlin MoE

* Use attention kernels from the Hub

* Cache the kernels in the Docker image

* Update moe kernels

* Support loading local kernels for development

* Support latest moe kernels

* Update to moe 0.1.1

* CI: download locked kernels for server tests

* Fixup some imports

* CI: activate venv

* Fix unused imports

* Nix: add attention/moe/quantization kernels

* Update hf-kernels to 0.1.5

* Update kernels

* Update tgi-nix flake for hf-kernels

* Fix EOF

* Take `load_kernel` out of a frequently-called function

* Hoist another case of kernel loading out of a somewhat hot function

* marlin-kernels -> quantization

* attention -> paged-attention

* EOF fix

* Update hf-kernels, fixup Docker

* ipex fix

* Remove outdated TODO
2025-02-10 19:19:25 +01:00
Daniël de Kok
dd2bd5fdb3
impureWithCuda: fix gcc version (#2990)
* impureWithCuda: fix gcc version

* trufflehog: do not fail on unverified results
2025-02-04 17:01:59 +01:00
Daniël de Kok
07bed530f7
nix: build and cache impure devshells (#2765)
* nix: build and cache all devshells

* nix: add poetry to the impure shell

This shouldn't be used to manage dependencies in a Nix devshell, but can
be handy to update `poetry.lock`.

* Fix Nix build, disable pure shell (covered by Nix tests)
2024-11-20 20:56:11 +01:00
OlivierDehaene
03c9388bf7
feat: natively support Granite models (#2682)
* feat: natively support Granite models

* Update doc
2024-10-23 10:04:05 +00:00
Daniël de Kok
9c9ef37c56
Add impureWithCuda dev shell (#2677)
* Add `impureWithCuda` dev shell

This shell is handy when developing some kernels jointly with TGI - it
adds nvcc and a bunch of commonly-used CUDA libraries to the environment.

We don't add this to the normal impure shell to keep the development
environment as clean as possible (avoid accidental dependencies, etc.).

* Add cuDNN
2024-10-22 11:02:55 +02:00
Daniël de Kok
9ed0c85fe1
nix: add black and isort to the closure (#2619)
To make sure that everything is formatted with the same black version
as CI.

I sometimes use isort for new files to get nicely ordered imports,
so add it as well. Also set the isort configuration to format in a
way that is compatible with black.
2024-10-09 11:08:02 +02:00
Daniël de Kok
5b6b74e21d
Improve support for GPUs with capability < 8 (#2575)
* 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
2024-09-27 16:19:42 +02:00