| .. |
|
disagg_config_cache_aware_balance.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_cache_reuse.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_conditional.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_ctxtp1_gentp1_deepseek_v3_lite_one_mtp_attention_dp_overlap.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_ctxtp1_gentp1_deepseek_v3_lite_one_mtp.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_ctxtp1_gentp1_deepseek_v3_lite.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_ctxtp2_gentp1_trt_backend.yaml
|
[feat][TRTLLM-5018] Dis serving python runtime trt backend (#4243)
|
2025-05-22 22:01:06 -04:00 |
|
disagg_config_ctxtp2_gentp1.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_ctxtp2_gentp2_deepseek_v3_lite_attention_dp_one_mtp.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_ctxtp2_gentp2_deepseek_v3_lite_attention_dp_one.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_ctxtp2_gentp2_deepseek_v3_lite_attention_dp_overlap_cuda_graph.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_ctxtp2_gentp2_deepseek_v3_lite_attention_dp_overlap.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_ctxtp2_gentp2_deepseek_v3_lite_attention_dp.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_ctxtp2_gentp2_deepseek_v3_lite_overlap_cuda_graph.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_ctxtp2_gentp2_deepseek_v3_lite.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_cuda_graph_padding.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_gen_only_trt_backend.yaml
|
[feat][TRTLLM-5018] Dis serving python runtime trt backend (#4243)
|
2025-05-22 22:01:06 -04:00 |
|
disagg_config_gen_only.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_load_balance.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_mixed.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_overlap.yaml
|
chore [BREAKING CHANGE]: Flatten PyTorchConfig knobs into TorchLlmArgs (#4603)
|
2025-05-28 18:43:04 +08:00 |
|
disagg_config_trt_backend.yaml
|
[feat][TRTLLM-5018] Dis serving python runtime trt backend (#4243)
|
2025-05-22 22:01:06 -04:00 |