Skip to content

Actions: AutoGPTQ/AutoGPTQ

Actions

All workflows

Actions

Loading...

Showing runs from all workflows
400 workflow runs
400 workflow runs
Event

Filter by event
Status

Filter by status
Branch
Actor

Filter by actor
added 5,6,7 bit quantization support check_code_quality #264: Pull request #676 synchronize by thoorpukarnakar
May 22, 2024 11:31 Action required thoorpukarnakar:main
thoorpukarnakar:main
May 22, 2024 11:31 Action required
added 5,6,7 bit quantization support check_code_quality #263: Pull request #676 opened by thoorpukarnakar
May 21, 2024 08:22 Action required thoorpukarnakar:main
thoorpukarnakar:main
May 21, 2024 08:22 Action required
Fix transformers 4.38.0 seq_len check_code_quality #262: Pull request #668 opened by randoentity
May 11, 2024 05:36 Action required randoentity:fix-transformers-4.38.0-seq_len
randoentity:fix-transformers-4.38.0-seq_len
May 11, 2024 05:36 Action required
[SYCL] Intel SYCL runtime support for AutoGPTQ check_code_quality #261: Pull request #638 synchronize by abhilash1910
May 8, 2024 07:04 Action required abhilash1910:sycl
abhilash1910:sycl
May 8, 2024 07:04 Action required
[FEATURE] Support BitBLAS Backend for QuantLinear check_code_quality #260: Pull request #662 opened by LeiWang1999
May 1, 2024 18:38 Action required LeiWang1999:bitblas
LeiWang1999:bitblas
May 1, 2024 18:38 Action required
Support QBits kernel for CPU device check_code_quality #259: Pull request #660 opened by PenghuiCheng
April 29, 2024 09:39 Action required PenghuiCheng:support_CPU_device
PenghuiCheng:support_CPU_device
April 29, 2024 09:39 Action required
[BUG/DEPRECATION] Remove fused attention/mlp check_code_quality #258: Pull request #659 synchronize by Qubitium
April 28, 2024 16:38 Action required Qubitium:remove-fused-attention
Qubitium:remove-fused-attention
April 28, 2024 16:38 Action required
[BUG/DEPRECATION] Remove fused attention/mlp check_code_quality #257: Pull request #659 opened by Qubitium
April 28, 2024 16:31 Action required Qubitium:remove-fused-attention
Qubitium:remove-fused-attention
April 28, 2024 16:31 Action required
[DEPRECATION] Remove triton v1 check_code_quality #256: Pull request #658 synchronize by Qubitium
April 28, 2024 15:55 Action required Qubitium:remove-triton-v1
Qubitium:remove-triton-v1
April 28, 2024 15:55 Action required
[DEPRECATION] Remove triton v1 check_code_quality #255: Pull request #658 synchronize by Qubitium
April 28, 2024 15:54 Action required Qubitium:remove-triton-v1
Qubitium:remove-triton-v1
April 28, 2024 15:54 Action required
[DEPRECATION] Remove triton v1 check_code_quality #254: Pull request #658 synchronize by Qubitium
April 28, 2024 15:40 Action required Qubitium:remove-triton-v1
Qubitium:remove-triton-v1
April 28, 2024 15:40 Action required
[DEPRECATION] Remove triton v1 check_code_quality #253: Pull request #658 opened by Qubitium
April 28, 2024 15:37 Action required Qubitium:remove-triton-v1
Qubitium:remove-triton-v1
April 28, 2024 15:37 Action required
[USABILITY] Warn users if quantization using insufficient nsamples check_code_quality #252: Pull request #656 opened by Qubitium
April 28, 2024 03:05 Action required Qubitium:nsamples-sanity-check
Qubitium:nsamples-sanity-check
April 28, 2024 03:05 Action required
[BUG] Fix H100 crash/compat with Marlin check_code_quality #251: Pull request #654 synchronize by Qubitium
April 27, 2024 15:08 Action required Qubitium:fix-h100
Qubitium:fix-h100
April 27, 2024 15:08 Action required
[BUG] Fix H100 crash/compat with Marlin check_code_quality #250: Pull request #654 synchronize by Qubitium
April 27, 2024 14:57 Action required Qubitium:fix-h100
Qubitium:fix-h100
April 27, 2024 14:57 Action required
[FEATURE] Allow loading of quantized lm_head check_code_quality #249: Pull request #648 synchronize by Qubitium
April 27, 2024 11:24 Action required Qubitium:quantize-lm-head
Qubitium:quantize-lm-head
April 27, 2024 11:24 Action required
[BUG/FEATURE] Fix Sym=False, new checkpoint_format = gptq_v2 check_code_quality #248: Pull request #640 synchronize by Qubitium
April 27, 2024 06:45 Action required Qubitium:sym-false
Qubitium:sym-false
April 27, 2024 06:45 Action required
[BUG/FEATURE] Fix Sym=False, new checkpoint_format = gptq_v2 check_code_quality #247: Pull request #640 synchronize by Qubitium
April 27, 2024 06:40 Action required Qubitium:sym-false
Qubitium:sym-false
April 27, 2024 06:40 Action required
Extend support for Phi-3 models check_code_quality #246: Pull request #651 opened by davidgxue
April 27, 2024 03:56 Action required davidgxue:add-phi3-support
davidgxue:add-phi3-support
April 27, 2024 03:56 Action required
[BUG/FEATURE] Fix Sym=False, new checkpoint_format = gptq_v2 check_code_quality #197: Pull request #640 synchronize by fxmarty
April 15, 2024 12:31 8m 46s Qubitium:sym-false
Qubitium:sym-false
April 15, 2024 12:31 8m 46s
Force warn users to reduce threads or packing may regress ~100x (#628) check_code_quality #161: Commit ea829c7 pushed by fxmarty
April 12, 2024 09:11 11m 53s main
main
April 12, 2024 09:11 11m 53s
pages build and deployment pages-build-deployment #144: by fxmarty
April 12, 2024 09:11 54s
April 12, 2024 09:11 54s
Cohere Command-R Added (#631) check_code_quality #160: Commit ce39d61 pushed by fxmarty
April 12, 2024 08:59 8m 45s main
main
April 12, 2024 08:59 8m 45s
pages build and deployment pages-build-deployment #143: by fxmarty
April 12, 2024 08:59 39s
April 12, 2024 08:59 39s
Fix padding not used correctly in exllama v2 layer (#626) check_code_quality #158: Commit b4b801c pushed by fxmarty
April 5, 2024 08:48 1m 26s main
main
April 5, 2024 08:48 1m 26s