refactor(tinygrad): reuse tinygrad.apps.llm instead of vendored Transformer (#9380)

Drop the 295-line vendor/llama.py fork in favor of `tinygrad.apps.llm`,
which now provides the Transformer blocks, GGUF loader (incl. Q4/Q6/Q8
quantization), KV-cache and generate loop we were maintaining ourselves.

What changed:
- New vendor/appsllm_adapter.py (~90 LOC) — HF -> GGUF-native state-dict
  keymap, Transformer kwargs builder, `_embed_hidden` helper, and a hard
  rejection of qkv_bias models (Qwen2 / 2.5 are no longer supported; the
  apps.llm Transformer ties `bias=False` on Q/K/V projections).
- backend.py routes both safetensors and GGUF paths through
  apps.llm.Transformer. Generation now delegates to its (greedy-only)
  `generate()`; Temperature / TopK / TopP / RepetitionPenalty are still
  accepted on the wire but ignored — documented in the module docstring.
- Jinja chat render now passes `enable_thinking=False` so Qwen3's
  reasoning preamble doesn't eat the tool-call token budget on small
  models.
- Embedding path uses `_embed_hidden` (block stack + output_norm) rather
  than the custom `embed()` method we were carrying on the vendored
  Transformer.
- test.py gains TestAppsLLMAdapter covering the keymap rename, tied
  embedding fallback, unknown-key skipping, and qkv_bias rejection.
- Makefile fixtures move from Qwen/Qwen2.5-0.5B-Instruct to Qwen/Qwen3-0.6B
  (apps.llm-compatible) and tool_parser from qwen3_xml to hermes (the
  HF chat template emits hermes-style JSON tool calls).

Verified with the docker-backed targets:
  test-extra-backend-tinygrad             5/5 PASS
  test-extra-backend-tinygrad-embeddings  3/3 PASS
  test-extra-backend-tinygrad-whisper     4/4 PASS
  test-extra-backend-tinygrad-sd          3/3 PASS

Author: mudler

Makefile

@@ -560,18 +560,18 @@ test-extra-backend-vllm: docker-build-vllm
 ## the `test-extra-backend-tinygrad-all` aggregate.
 test-extra-backend-tinygrad: docker-build-tinygrad
 	BACKEND_IMAGE=local-ai-backend:tinygrad \
-	BACKEND_TEST_MODEL_NAME=Qwen/Qwen2.5-0.5B-Instruct \
+	BACKEND_TEST_MODEL_NAME=Qwen/Qwen3-0.6B \
 	BACKEND_TEST_CAPS=health,load,predict,stream,tools \
 	BACKEND_TEST_OPTIONS=tool_parser:hermes \
 	$(MAKE) test-extra-backend
 
 ## tinygrad — embeddings via LLM last-hidden-state pooling. Reuses the same
-## Qwen2.5-0.5B-Instruct as the chat target so we don't need a separate BERT
-## vendor; the Embedding RPC mean-pools and L2-normalizes the last-layer
-## hidden state.
+## Qwen3-0.6B as the chat target so we don't need a separate BERT vendor;
+## the Embedding RPC mean-pools and L2-normalizes the last-layer hidden
+## state.
 test-extra-backend-tinygrad-embeddings: docker-build-tinygrad
 	BACKEND_IMAGE=local-ai-backend:tinygrad \
-	BACKEND_TEST_MODEL_NAME=Qwen/Qwen2.5-0.5B-Instruct \
+	BACKEND_TEST_MODEL_NAME=Qwen/Qwen3-0.6B \
 	BACKEND_TEST_CAPS=health,load,embeddings \
 	$(MAKE) test-extra-backend