anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Feature]: Remove some useless hf_overrides in yaml (#1898)

Browse Source 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
This commit is contained in:
汪志鹏 authored and GitHub committed 2026-03-18 19:46:44 +08:00
1 parent f52b51533a
commit 61e170c69a
8 files changed
-38
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

benchmarks/qwen3-tts/vllm_omni/configs/qwen3_tts_bs1.yaml
-4
View File
@@ -10,8 +10,6 @@ stage_args:
engine_args:
model_stage: qwen3_tts
model_arch: Qwen3TTSTalkerForConditionalGeneration
hf_overrides:
architectures: [Qwen3TTSTalkerForConditionalGeneration]
worker_type: ar
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
enforce_eager: false
@@ -43,8 +41,6 @@ stage_args:
engine_args:
model_stage: code2wav
model_arch: Qwen3TTSCode2Wav
hf_overrides:
architectures: [Qwen3TTSCode2Wav]
worker_type: generation
scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler
enforce_eager: true
benchmarks/qwen3-tts/vllm_omni/configs/qwen3_tts_bs4.yaml
-4
View File
@@ -11,8 +11,6 @@ stage_args:
engine_args:
model_stage: qwen3_tts
model_arch: Qwen3TTSTalkerForConditionalGeneration
hf_overrides:
architectures: [Qwen3TTSTalkerForConditionalGeneration]
worker_type: ar
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
enforce_eager: false
@@ -44,8 +42,6 @@ stage_args:
engine_args:
model_stage: code2wav
model_arch: Qwen3TTSCode2Wav
hf_overrides:
architectures: [Qwen3TTSCode2Wav]
worker_type: generation
scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler
enforce_eager: true
tests/perf/stage_configs/qwen3_tts.yaml
-4
View File
@@ -14,8 +14,6 @@ stage_args:
engine_args:
model_stage: qwen3_tts
model_arch: Qwen3TTSTalkerForConditionalGeneration
hf_overrides:
architectures: [Qwen3TTSTalkerForConditionalGeneration]
worker_type: ar
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
enforce_eager: false
@@ -47,8 +45,6 @@ stage_args:
engine_args:
model_stage: code2wav
model_arch: Qwen3TTSCode2Wav
hf_overrides:
architectures: [Qwen3TTSCode2Wav]
worker_type: generation
scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler
enforce_eager: true
vllm_omni/model_executor/stage_configs/fish_speech_s2_pro.yaml
-4
View File
@@ -8,8 +8,6 @@ stage_args:
engine_args:
model_stage: fish_speech_slow_ar
model_arch: FishSpeechSlowARForConditionalGeneration
hf_overrides:
architectures: [FishSpeechSlowARForConditionalGeneration]
worker_type: ar
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
enforce_eager: false
@@ -43,8 +41,6 @@ stage_args:
engine_args:
model_stage: dac_decoder
model_arch: FishSpeechDACDecoder
hf_overrides:
architectures: [FishSpeechDACDecoder]
worker_type: generation
scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler
enforce_eager: true
vllm_omni/model_executor/stage_configs/qwen3_tts.yaml
-6
View File
@@ -9,9 +9,6 @@ stage_args:
engine_args:
model_stage: qwen3_tts
model_arch: Qwen3TTSTalkerForConditionalGeneration
# Force stage-specific registered architecture.
hf_overrides:
architectures: [Qwen3TTSTalkerForConditionalGeneration]
worker_type: ar
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
enforce_eager: false
@@ -44,9 +41,6 @@ stage_args:
engine_args:
model_stage: code2wav
model_arch: Qwen3TTSCode2Wav
# Force stage-specific registered architecture.
hf_overrides:
architectures: [Qwen3TTSCode2Wav]
worker_type: generation
scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler
enforce_eager: true
vllm_omni/model_executor/stage_configs/qwen3_tts_batch.yaml
-6
View File
@@ -13,9 +13,6 @@ stage_args:
engine_args:
model_stage: qwen3_tts
model_arch: Qwen3TTSTalkerForConditionalGeneration
# Force stage-specific registered architecture.
hf_overrides:
architectures: [Qwen3TTSTalkerForConditionalGeneration]
worker_type: ar
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
enforce_eager: false
@@ -48,9 +45,6 @@ stage_args:
engine_args:
model_stage: code2wav
model_arch: Qwen3TTSCode2Wav
# Force stage-specific registered architecture.
hf_overrides:
architectures: [Qwen3TTSCode2Wav]
worker_type: generation
scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler
enforce_eager: true
vllm_omni/model_executor/stage_configs/qwen3_tts_no_async_chunk.yaml
-4
View File
@@ -9,8 +9,6 @@ stage_args:
engine_args:
model_stage: qwen3_tts
model_arch: Qwen3TTSTalkerForConditionalGeneration
hf_overrides:
architectures: [Qwen3TTSTalkerForConditionalGeneration]
worker_type: ar
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
enforce_eager: false
@@ -39,8 +37,6 @@ stage_args:
engine_args:
model_stage: code2wav
model_arch: Qwen3TTSCode2Wav
hf_overrides:
architectures: [Qwen3TTSCode2Wav]
worker_type: generation
scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler
enforce_eager: true
vllm_omni/platforms/npu/stage_configs/qwen3_tts.yaml
-6
View File
@@ -9,9 +9,6 @@ stage_args:
engine_args:
model_stage: qwen3_tts
model_arch: Qwen3TTSTalkerForConditionalGeneration
# Force stage-specific registered architecture.
hf_overrides:
architectures: [Qwen3TTSTalkerForConditionalGeneration]
worker_type: ar
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
enforce_eager: true
@@ -44,9 +41,6 @@ stage_args:
engine_args:
model_stage: code2wav
model_arch: Qwen3TTSCode2Wav
# Force stage-specific registered architecture.
hf_overrides:
architectures: [Qwen3TTSCode2Wav]
worker_type: generation
scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler
enforce_eager: true