[Mini-VLLM] Remove LoRA, plugins, speech-to-text and scale-out surfaces
Production runs one static model behind the OpenAI-compatible API. Every adapter path and non-OpenAI HTTP surface is unreachable there. - Delete the LoRA stack: vllm/lora, LoRARequest on the engine wire, the scheduler, worker, cudagraph and MoE plumbing, LoRA metrics, the lora CLI group, and the LoRA tests. - Drop the plugin loader in vllm/plugins. Platform resolution is now CUDA-only and the general/stat-logger plugin hooks are gone. - Delete the speech-to-text and realtime entrypoints, the scale-out render routes, and vllm/config/speech_to_text.py. GenerationTask is generate-only. - Cut DecodeBenchConnector and the disagg-prefill doc and image. The Multi, Offloading and Example connectors stay; production uses the CPU KV offload tier. - Delete the ROCm-only fused KDA chunk kernel (2346 lines) with its CMake arch gate, declarations and op registrations. The CUDA build never defined the guard and no Python caller existed. - Delete the orphan Mistral and Pixtral chat fixtures and examples/. - Fix _check_model: removing the LoRA early return made every request fail with "The model ... does not exist. Valid aliases: ...". Verified on an RTX 3090: import sweep reports 1242 modules with 7 known optional-dependency failures; a live server answers chat, completions, responses, tokenize and detokenize with zero log errors and 404 for the removed surfaces; collection yields 8558 tests with the 3 pre-existing errors; ruff adds no new finding; the incremental _C build succeeds. Co-authored-by: Hinata <hinata@idihore.id> Signed-off-by: MOVZX <movzx@yahoo.com>
This commit is contained in:
@@ -43,18 +43,6 @@ class BatchDescriptor:
|
||||
"""
|
||||
True if all the requests in the batch have the same number of tokens.
|
||||
"""
|
||||
has_lora: bool = False
|
||||
"""
|
||||
Whether this batch has active LoRA adapters.
|
||||
"""
|
||||
num_active_loras: int = 0
|
||||
"""
|
||||
Number of distinct active LoRA adapters in this batch.
|
||||
When cudagraph_specialize_lora_count is enabled, separate CUDA graphs
|
||||
are captured for each num_active_loras value. This allows kernels
|
||||
(like fused_moe_lora) whose grid size depends on num_active_loras
|
||||
to be properly captured.
|
||||
"""
|
||||
|
||||
|
||||
def _compute_sp_num_tokens(
|
||||
|
||||
Reference in New Issue
Block a user