Skip to content

Actions: huggingface/optimum-quanto

Linux CUDA tests

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
333 workflow runs
333 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ci: update workflows
Linux CUDA tests #68: Commit eb6b82d pushed by dacorvo
May 31, 2024 14:41 5m 4s main
May 31, 2024 14:41 5m 4s
Convert quanto to optimum-quanto
Linux CUDA tests #67: Pull request #205 synchronize by dacorvo
May 31, 2024 14:23 5m 9s namespace_package
May 31, 2024 14:23 5m 9s
Convert quanto to optimum-quanto
Linux CUDA tests #66: Pull request #205 synchronize by dacorvo
May 31, 2024 14:20 2m 16s namespace_package
May 31, 2024 14:20 2m 16s
Convert quanto to optimum-quanto
Linux CUDA tests #65: Pull request #205 opened by dacorvo
May 31, 2024 14:15 1m 51s namespace_package
May 31, 2024 14:15 1m 51s
fix(examples): pin transformers version
Linux CUDA tests #64: Commit 7de45a3 pushed by dacorvo
May 23, 2024 18:39 5m 45s main
May 23, 2024 18:39 5m 45s
Add latest AWQ CUDA fp16 int4 kernels
Linux CUDA tests #63: Pull request #198 synchronize by dacorvo
May 22, 2024 16:56 5m 18s awq_kernels
May 22, 2024 16:56 5m 18s
Add latest AWQ CUDA fp16 int4 kernels
Linux CUDA tests #62: Pull request #198 synchronize by dacorvo
May 22, 2024 13:13 5m 4s awq_kernels
May 22, 2024 13:13 5m 4s
Add latest AWQ CUDA fp16 int4 kernels
Linux CUDA tests #61: Pull request #198 opened by dacorvo
May 22, 2024 13:11 1m 48s awq_kernels
May 22, 2024 13:11 1m 48s
feat(quantize): do not use a group_size lower than 128
Linux CUDA tests #60: Commit 934c4a7 pushed by dacorvo
May 16, 2024 15:36 5m 9s main
May 16, 2024 15:36 5m 9s
Prepare for gemm kernels
Linux CUDA tests #59: Pull request #197 opened by dacorvo
May 16, 2024 15:19 5m 19s prepare_for_gemm_kernels
May 16, 2024 15:19 5m 19s
fix: silence ruff warnings
Linux CUDA tests #58: Commit bb865e6 pushed by dacorvo
May 6, 2024 08:25 5m 26s main
May 6, 2024 08:25 5m 26s
Silence ruff warnings
Linux CUDA tests #57: Pull request #196 opened by dacorvo
May 6, 2024 08:25 8m 52s ruff_warning
May 6, 2024 08:25 8m 52s
refactor(qtensor): clarify dispatch
Linux CUDA tests #56: Commit ff48f8d pushed by dacorvo
May 6, 2024 08:22 8m 46s main
May 6, 2024 08:22 8m 46s
Clarify dispatch
Linux CUDA tests #55: Pull request #195 opened by dacorvo
May 6, 2024 08:08 5m 46s refactor_dispatch
May 6, 2024 08:08 5m 46s
test(compile): still not working with pt 2.3.0
Linux CUDA tests #54: Commit 6e44e96 pushed by dacorvo
May 3, 2024 15:32 5m 40s main
May 3, 2024 15:32 5m 40s
Yet another tensor refactoring
Linux CUDA tests #53: Pull request #193 synchronize by dacorvo
May 3, 2024 14:17 5m 25s yet_another_tensor_refactoring
May 3, 2024 14:17 5m 25s
Yet another tensor refactoring
Linux CUDA tests #52: Pull request #193 opened by dacorvo
May 3, 2024 13:58 5m 25s yet_another_tensor_refactoring
May 3, 2024 13:58 5m 25s
refactor(quanto): avoid qlinear composite gradients
Linux CUDA tests #51: Commit 1f0a2a5 pushed by dacorvo
April 23, 2024 13:36 5m 31s main
April 23, 2024 13:36 5m 31s
Avoid composite gradients in quantized linear function
Linux CUDA tests #50: Pull request #187 opened by dacorvo
April 23, 2024 09:35 5m 20s explicit_qlinear_gradient
April 23, 2024 09:35 5m 20s
Fix serialization
Linux CUDA tests #49: Pull request #120 reopened by SunMarc
April 22, 2024 13:16 1m 52s fix-serialization
April 22, 2024 13:16 1m 52s
build: fix pyproject.toml
Linux CUDA tests #48: Pull request #185 opened by baggiponte
April 21, 2024 18:23 1m 55s baggiponte:build/remove-setup.py
April 21, 2024 18:23 1m 55s
review: removed accelerate check. also now moving model back to origi…
Linux CUDA tests #47: Commit 544981d pushed by dacorvo
April 18, 2024 12:39 8m 49s main
April 18, 2024 12:39 8m 49s
Feat: Added requantize function and tests
Linux CUDA tests #46: Pull request #171 synchronize by calmitchell617
April 18, 2024 08:51 3h 22m 36s calmitchell617:requantize-function
April 18, 2024 08:51 3h 22m 36s
Feat: Added requantize function and tests
Linux CUDA tests #44: Pull request #171 synchronize by calmitchell617
April 18, 2024 08:30 1m 48s calmitchell617:requantize-function
April 18, 2024 08:30 1m 48s
refactor(group): align terminology
Linux CUDA tests #42: Commit 8e16e79 pushed by dacorvo
April 16, 2024 16:11 6m 9s main
April 16, 2024 16:11 6m 9s
ProTip! You can narrow down the results and go further in time using created:<2024-04-16 or the other filters available.