text-generation-inference/.github/workflows
Nicolas Patry d6881c37ab
Putting back the NCCL forced upgrade. (#2999)
* Putting back the NCCL forced upgrade.

* .

* ...

* Ignoring conda.

* Dropping conda from the buidl system + torch 2.6

* Cache min.

* Rolling back torch version.

* Reverting the EETQ modification.

* Fix flash attention ?

* Actually stay on flash v1.

* Patching flash v1.

* Torch 2.6, fork of rotary, eetq updated.

* Put back nccl latest (override torch).

* Slightly more reproducible build and not as scary.
2025-02-14 11:31:59 +01:00
..
autodocs.yaml Rebase TRT-llm (#2331) 2024-07-31 10:33:10 +02:00
build_documentation.yaml New runner. Manual squash. (#2110) 2024-06-24 18:08:34 +02:00
build_pr_documentation.yaml doc: Add metrics documentation and add a 'Reference' section (#2230) 2024-08-16 19:43:30 +02:00
build.yaml Putting back the NCCL forced upgrade. (#2999) 2025-02-14 11:31:59 +01:00
ci_build.yaml Give TensorRT-LLMa proper CI/CD 😍 (#2886) 2025-01-21 10:19:16 +01:00
client-tests.yaml Removing IPEX_AVAIL. (#2115) 2024-06-25 13:20:57 +02:00
integration_tests.yaml Removing IPEX_AVAIL. (#2115) 2024-06-25 13:20:57 +02:00
load_test.yaml feat: Add automatic nightly benchmarks (#2591) 2024-11-21 17:11:42 +00:00
nix_cache.yaml nix: build and cache impure devshells (#2765) 2024-11-20 20:56:11 +01:00
nix_tests.yaml Stream options. (#2533) 2024-09-19 20:50:37 +02:00
stale.yaml New runner. Manual squash. (#2110) 2024-06-24 18:08:34 +02:00
tests.yaml Use kernels from the kernel hub (#2988) 2025-02-10 19:19:25 +01:00
trufflehog.yaml impureWithCuda: fix gcc version (#2990) 2025-02-04 17:01:59 +01:00
upload_pr_documentation.yaml New runner. Manual squash. (#2110) 2024-06-24 18:08:34 +02:00