llama-cpp-bindings/Makefile at main · intentee/llama-cpp-bindings · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
FEATURES = sampler
TEST_FEATURES =
QWEN_CAPABLE_FEATURES = multimodal_capable,mrope_model
CARGO_TEST_LLM_FLAGS = --no-fail-fast -p llama-cpp-bindings-tests $(if $(TEST_FEATURES),--features $(TEST_FEATURES),) -- --test-threads=1
CARGO_TEST_LLM_FLAGS_QWEN_CAPABLE = --no-fail-fast -p llama-cpp-bindings-tests $(if $(TEST_FEATURES),--features $(TEST_FEATURES),) --features $(QWEN_CAPABLE_FEATURES) -- --test-threads=1

QWEN3_5_0_8B_ENV = \
	LLAMA_TEST_HF_REPO=unsloth/Qwen3.5-0.8B-GGUF \
	LLAMA_TEST_HF_MODEL=Qwen3.5-0.8B-Q4_K_M.gguf \
	LLAMA_TEST_HF_MMPROJ=mmproj-F16.gguf \
	LLAMA_TEST_HF_EMBED_REPO=Qwen/Qwen3-Embedding-0.6B-GGUF \
	LLAMA_TEST_HF_EMBED_MODEL=Qwen3-Embedding-0.6B-Q8_0.gguf \
	LLAMA_TEST_HF_ENCODER_REPO=Xiaojian9992024/t5-small-GGUF \
	LLAMA_TEST_HF_ENCODER_MODEL=t5-small.bf16.gguf

QWEN3_6_35B_A3B_ENV = \
	LLAMA_TEST_HF_REPO=unsloth/Qwen3.6-35B-A3B-GGUF \
	LLAMA_TEST_HF_MODEL=Qwen3.6-35B-A3B-UD-Q4_K_M.gguf \
	LLAMA_TEST_HF_MMPROJ=mmproj-F16.gguf \
	LLAMA_TEST_HF_EMBED_REPO=Qwen/Qwen3-Embedding-0.6B-GGUF \
	LLAMA_TEST_HF_EMBED_MODEL=Qwen3-Embedding-0.6B-Q8_0.gguf \
	LLAMA_TEST_HF_ENCODER_REPO=Xiaojian9992024/t5-small-GGUF \
	LLAMA_TEST_HF_ENCODER_MODEL=t5-small.bf16.gguf

GLM4_7_FLASH_ENV = \
	LLAMA_TEST_HF_REPO=unsloth/GLM-4.7-Flash-GGUF \
	LLAMA_TEST_HF_MODEL=GLM-4.7-Flash-Q4_K_M.gguf \
	LLAMA_TEST_HF_EMBED_REPO=Qwen/Qwen3-Embedding-0.6B-GGUF \
	LLAMA_TEST_HF_EMBED_MODEL=Qwen3-Embedding-0.6B-Q8_0.gguf \
	LLAMA_TEST_HF_ENCODER_REPO=Xiaojian9992024/t5-small-GGUF \
	LLAMA_TEST_HF_ENCODER_MODEL=t5-small.bf16.gguf

DEEPSEEK_R1_DISTILL_LLAMA_8B_ENV = \
	LLAMA_TEST_HF_REPO=unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF \
	LLAMA_TEST_HF_MODEL=DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf \
	LLAMA_TEST_HF_EMBED_REPO=Qwen/Qwen3-Embedding-0.6B-GGUF \
	LLAMA_TEST_HF_EMBED_MODEL=Qwen3-Embedding-0.6B-Q8_0.gguf \
	LLAMA_TEST_HF_ENCODER_REPO=Xiaojian9992024/t5-small-GGUF \
	LLAMA_TEST_HF_ENCODER_MODEL=t5-small.bf16.gguf

.PHONY: test.unit
test.unit: clippy
	cargo test -p llama-cpp-bindings --features $(FEATURES)

.PHONY: test.deepseek_r1_distill_llama_8b
test.deepseek_r1_distill_llama_8b: clippy
	$(DEEPSEEK_R1_DISTILL_LLAMA_8B_ENV) cargo test $(CARGO_TEST_LLM_FLAGS)

.PHONY: test.glm4_7_flash
test.glm4_7_flash: clippy
	$(GLM4_7_FLASH_ENV) cargo test $(CARGO_TEST_LLM_FLAGS)

.PHONY: test.qwen3.5_0.8B
test.qwen3.5_0.8B: clippy
	$(QWEN3_5_0_8B_ENV) cargo test $(CARGO_TEST_LLM_FLAGS_QWEN_CAPABLE)

.PHONY: test.qwen3.6_35b_a3b
test.qwen3.6_35b_a3b: clippy
	$(QWEN3_6_35B_A3B_ENV) cargo test $(CARGO_TEST_LLM_FLAGS_QWEN_CAPABLE)

.PHONY: test.llms
test.llms: \
	test.deepseek_r1_distill_llama_8b \
	test.glm4_7_flash \
	test.qwen3.5_0.8B \
	test.qwen3.6_35b_a3b

.PHONY: test
test: test.unit test.llms

.PHONY: fmt
fmt:
	cargo fmt --all --check

.PHONY: clippy
clippy:
	cargo clippy --all-targets -p llama-cpp-bindings --features $(FEATURES) -- -D warnings
	cargo clippy --all-targets -p llama-cpp-bindings-tests $(if $(TEST_FEATURES),--features $(TEST_FEATURES),) -- -D warnings

.PHONY: clean.cmake
clean.cmake:
	rm -rf target/llama-cpp-cmake-build