[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:
@@ -424,25 +424,6 @@ STABLE_TORCH_LIBRARY_FRAGMENT(_C, ops) {
|
||||
"str output_gate_activation='silu') -> ()");
|
||||
#endif
|
||||
|
||||
#ifdef VLLM_ENABLE_FUSED_KDA_CHUNK
|
||||
ops.def(
|
||||
"fused_kda_prologue("
|
||||
"Tensor q, Tensor k, Tensor v, Tensor raw_g, Tensor raw_beta, "
|
||||
"Tensor A_log, Tensor dt_bias, Tensor! qg, Tensor! w, Tensor! u, "
|
||||
"Tensor! kg_t, Tensor! aqk, Tensor! decay, Tensor cu_seqlens, "
|
||||
"Tensor chunk_indices, Tensor? conv_weight, Tensor(e!)? conv_state, "
|
||||
"Tensor? conv_state_indices, Tensor? conv_has_initial_state, "
|
||||
"float scale, float lower_bound) -> ()");
|
||||
ops.def(
|
||||
"fused_kda_chunk("
|
||||
"Tensor qg, Tensor w, Tensor u, Tensor kg_t, Tensor aqk, Tensor decay, "
|
||||
"Tensor? initial_state, Tensor(a!)? final_state, Tensor! out, "
|
||||
"Tensor cu_seqlens, Tensor chunk_offsets, float scale, "
|
||||
"Tensor(b!)? group_state, int groups, "
|
||||
"Tensor(c!)? checkpoint_state=None, Tensor? checkpoint_offsets=None, "
|
||||
"Tensor? checkpoint_state_indices=None, Tensor(d!)? state_cache=None, "
|
||||
"Tensor? state_indices=None, Tensor? has_initial_state=None) -> ()");
|
||||
#endif
|
||||
|
||||
// Apply repetition penalties to logits in-place.
|
||||
ops.def(
|
||||
@@ -684,10 +665,6 @@ STABLE_TORCH_LIBRARY_IMPL(_C, CUDA, ops) {
|
||||
TORCH_BOX(&fused_gdn_decode_post_conv_mtp));
|
||||
#endif
|
||||
|
||||
#ifdef VLLM_ENABLE_FUSED_KDA_CHUNK
|
||||
ops.impl("fused_kda_prologue", TORCH_BOX(&fused_kda_prologue));
|
||||
ops.impl("fused_kda_chunk", TORCH_BOX(&fused_kda_chunk));
|
||||
#endif
|
||||
|
||||
// Sampler kernels (shared CUDA/ROCm)
|
||||
ops.impl("apply_repetition_penalties_",
|
||||
|
||||
Reference in New Issue
Block a user