requirements/rocm.txt

# Common dependencies
-r common.txt

numba == 0.61.2 # Required for N-gram speculative decoding

# Dependencies for AMD GPUs
datasets
ray[cgraph]>=2.48.0 # Ray Compiled Graph, required for pipeline parallelism in V1.
peft
pytest-asyncio
tensorizer==2.10.1
packaging>=24.2
setuptools>=77.0.3,<80.0.0
setuptools-scm>=8
runai-model-streamer[s3,gcs]==0.15.0
conch-triton-kernels==1.2.1
timm>=1.0.17
fastsafetensors @ git+https://github.com/foundation-model-stack/fastsafetensors.git@d6f998a03432b2452f8de2bb5cefb5af9795d459
[Misc] Define common requirements (#3841) 2024-04-05 00:39:17 -07:00			`# Common dependencies`
Move requirements into their own directory (#12547) Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> 2025-03-08 17:44:35 +01:00			`-r common.txt`
[Misc] Define common requirements (#3841) 2024-04-05 00:39:17 -07:00
Remove Python 3.9 support ahead of PyTorch 2.9 in v0.11.1 (#26416) Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> 2025-10-08 18:40:42 +01:00			`numba == 0.61.2 # Required for N-gram speculative decoding`
Moved numba from common requirements to cuda/rocm specific requirements (#14199) Signed-off-by: Nishidha Panpaliya <nishidha.panpaliya@partner.ibm.com> 2025-03-05 09:55:00 +05:30
[Misc] Define common requirements (#3841) 2024-04-05 00:39:17 -07:00			`# Dependencies for AMD GPUs`
[ci/build] Fix AMD CI dependencies (#11087) 2024-12-11 00:39:53 -08:00			`datasets`
[ROCm][Feature] Enable Pipeline Parallelism with Ray Compiled Graph on ROCm (#24275) Signed-off-by: charlifu <charlifu@amd.com> 2025-09-09 18:27:35 -05:00			`ray[cgraph]>=2.48.0 # Ray Compiled Graph, required for pipeline parallelism in V1.`
[Bugfix][CI/Build][Hardware][AMD] Fix AMD tests, add HF cache, update CK FA, add partially supported model notes (#6543) 2024-07-20 11:39:07 -05:00			`peft`
[Build/CI] Enabling AMD Entrypoints Test (#4834) Co-authored-by: Alexey Kondratiev <alexey.kondratiev@amd.com> 2024-05-20 13:29:28 -05:00			`pytest-asyncio`
[Frontend] [Core] Integrate Tensorizer in to S3 loading machinery, allow passing arbitrary arguments during save/load (#19619) Signed-off-by: Sanger Steel <sangersteel@gmail.com> Co-authored-by: Eta <esyra@coreweave.com> 2025-07-08 01:47:43 -04:00			`tensorizer==2.10.1`
[AMD] Update compatible packaging version (#19309) Signed-off-by: pramkuma <Pramendra.Kumar@amd.com> 2025-06-07 18:25:09 +05:30			`packaging>=24.2`
[ROCm][Bugfix] Revert removing setuptools version restriction (#28592) Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com> 2025-11-12 19:46:58 -05:00			`setuptools>=77.0.3,<80.0.0`
[AMD] Update compatible packaging version (#19309) Signed-off-by: pramkuma <Pramendra.Kumar@amd.com> 2025-06-07 18:25:09 +05:30			`setuptools-scm>=8`
[Feat] Adds runai distributed streamer (#27230) Signed-off-by: bbartels <benjamin@bartels.dev> Signed-off-by: Benjamin Bartels <benjamin@bartels.dev> Co-authored-by: omer-dayan <omdayan@nvidia.com> Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk> 2025-10-30 04:09:10 +00:00			`runai-model-streamer[s3,gcs]==0.15.0`
[ROCm] Add dependencies for ROCm (#24900) Signed-off-by: Yida Wu <yida.wu@amd.com> 2025-09-16 14:49:06 -05:00			`conch-triton-kernels==1.2.1`
Run:ai model streamer add GCS package support (#24909) Signed-off-by: Peter Schuurman <psch@google.com> 2025-10-01 20:59:13 -07:00			`timm>=1.0.17`
[BugFix] [FEAT] Enable fastsafetensors for ROCm platform (#28225) Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com> 2025-11-20 23:34:11 +07:00			`fastsafetensors @ git+https://github.com/foundation-model-stack/fastsafetensors.git@d6f998a03432b2452f8de2bb5cefb5af9795d459`