Skip to content

Actions: vllm-project/llm-compressor

Actions

PR Reminder Comment Bot

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
set-comment.yaml
897 workflow runs
897 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Fix KV cache calibration for attention modules not named self_attn PR Reminder Comment Bot #1108: Pull request #2477 opened by changjonathanc
23m 3s
23m 3s
Add logger_tqdm for integrated progress tracking PR Reminder Comment Bot #1107: Pull request #2476 opened by kylesayrs
7s
7s
correct model save name in example fp8 dynamic PR Reminder Comment Bot #1106: Pull request #2475 opened by HDCharles
7s
7s
correct model save name in example fp8 block PR Reminder Comment Bot #1105: Pull request #2474 opened by HDCharles
7s
7s
feat: add iMatrix weighted MSE observer and IMatrixGatherer PR Reminder Comment Bot #1104: Pull request #2473 opened by Yatimai
8m 51s
8m 51s
Move model parameters and buffers to CPU before offloading to prevent… PR Reminder Comment Bot #1103: Pull request #2472 opened by cubist38
35s
35s
[Distributed][SmoothQuant] Add distributed activation scale reduction (#2180) PR Reminder Comment Bot #1102: Pull request #2471 opened by dzhengAP
13s
13s
fix transformers v5 & ministral compatibility PR Reminder Comment Bot #1101: Pull request #2470 opened by leo-bujdei-leonte
6m 38s
6m 38s
[WIP] [DDP] Refactor quantization lifecycle for performance PR Reminder Comment Bot #1100: Pull request #2469 opened by kylesayrs
8s
8s
Deprecate is_rank0 PR Reminder Comment Bot #1099: Pull request #2468 opened by kylesayrs
17s
17s
[Examples] Add Qwen3.5-27B NVFP4A16 and MXFP4A16 quantization examples PR Reminder Comment Bot #1098: Pull request #2467 opened by 2imi9
9s
9s
Add DeepSeekV3 support for spinquant PR Reminder Comment Bot #1097: Pull request #2465 opened by carrot-o0o
7s
7s
[dev] split fused moe experts to ensure quantization PR Reminder Comment Bot #1096: Pull request #2464 opened by liwei109
7s
7s
[Warnings] Replace deprecated is_fx_tracing with is_fx_tracing_symbolic_tracing PR Reminder Comment Bot #1095: Pull request #2463 opened by kylesayrs
8s
8s
[Bugfix] QAC with basic pipeline PR Reminder Comment Bot #1094: Pull request #2462 opened by kylesayrs
7s
7s
[examples][awq] Update AWQ examples to stacked recipe pattern PR Reminder Comment Bot #1093: Pull request #2461 opened by dzhengAP
8s
8s
[do-not-merge] examples][awq] Update AWQ examples to stacked recipe pattern PR Reminder Comment Bot #1092: Pull request #2460 opened by dzhengAP
7s
7s
[do not merge] test failing ci/cd PR Reminder Comment Bot #1091: Pull request #2459 opened by brian-dellabetta
12s
12s
[AWQ][DDP] adding DDP functionality to AWQ PR Reminder Comment Bot #1090: Pull request #2457 opened by HDCharles
7s
7s
feat: defer activation qparam calculation to sequential epoch end PR Reminder Comment Bot #1089: Pull request #2455 opened by dzhengAP
1m 39s
1m 39s
Add GLQ (E8 lattice codebook) quantization modifier PR Reminder Comment Bot #1088: Pull request #2453 opened by cnygaard
1m 17s
1m 17s
[Compressors] Remove sparse compression PR Reminder Comment Bot #1087: Pull request #2452 opened by kylesayrs
6s
6s
[AWQ] Update MoE mappings to include router in balance layers PR Reminder Comment Bot #1086: Pull request #2451 opened by brian-dellabetta
2m 42s
2m 42s
[MoE][ddp] Enable distributed MoE calibration replacement PR Reminder Comment Bot #1085: Pull request #2449 opened by dichn
8s
8s
[model_free_ptq] Multi-gpu support, validate on meta model PR Reminder Comment Bot #1084: Pull request #2448 opened by kylesayrs
9s
9s