 jmorganca
|
fba7f04ca0
ml/backend/ggml: optionally evaluate os.Executable() symlinks
|
3 months ago |
|
Jeffrey Morgan
|
f05774b04c
llm: do not evaluate symlink for exe path lookup (#9088)
|
3 months ago |
|
Jeffrey Morgan
|
6600bd7d91
ml/backend/ggml: stable sort devices by score (#9081)
|
3 months ago |
 Jesse Gross
|
ed443a0393
Runner for Ollama engine
|
5 months ago |
|
Jesse Gross
|
6945617af5
models: Move model into their own directory
|
3 months ago |
|
Jesse Gross
|
7916f55009
vocab: Use int32 for special tokens
|
3 months ago |
|
Jesse Gross
|
d650ad398f
model: Load tensors behind an interface
|
4 months ago |
|
Jesse Gross
|
d223f3b697
ggml-backend: Close on nil should be a no-op
|
3 months ago |
|
Jesse Gross
|
60830695c2
ggml-backend: Ensure data is available after async computation
|
3 months ago |
|
Jesse Gross
|
01d9a46854
ggml-backend: Let GGML allocate context memory
|
3 months ago |
|
Jesse Gross
|
d773b7d671
backend: API to support full precision matmul
|
3 months ago |
|
Jesse Gross
|
4d4463b2bd
backend: Support graph computation that does not return an output
|
3 months ago |
|
Jesse Gross
|
0e38297f87
backend: Consistently use int (vs. int64) for tensor shapes
|
3 months ago |
|
Jesse Gross
|
7e13f568dc
backend: Don't return an error on Close
|
3 months ago |
 Michael Yang
|
58245413f4
next ollama runner (#7913)
|
3 months ago |
 Bùi Đức Nhật
|
8cf16063a5
docs: add ollamazing to the README.md (#9075)
|
3 months ago |
 frob
|
3a4449e2f1
docs: add H200 as supported device. (#9076)
|
3 months ago |
 Anuraag (Rag) Agrawal
|
10d59d5f90
openai: finish_reason as tool_calls for streaming with tools (#7963)
|
3 months ago |
|
Jeffrey Morgan
|
a4f69a0191
build: add -DGGML_CUDA_NO_PEER_COPY=ON for rocm builds on windows (#9060)
|
3 months ago |
 Clinton
|
82658c3eec
readme: add Homebrew to package managers section (#9052)
|
3 months ago |
 bloominstrong
|
378d6e1e6a
docs: fix nix package link (#9045)
|
3 months ago |
 Hugues Chocart
|
afa55bc70c
doc: fix link for Abso (#9043)
|
3 months ago |
|
Michael Yang
|
49df03da9a
fix: harden backend loading (#9024)
|
3 months ago |
|
Hugues Chocart
|
0189bdd0b7
readme: add Abso SDK to community integrations (#8973)
|
3 months ago |
|
Jeffrey Morgan
|
f4711da7bd
ml/backend/ggml: fix crash on dlopen for non-AVX systems (#8976)
|
3 months ago |
|
Hugues Chocart
|
38117fba83
readme: add Lunary to observability community integrations (#8975)
|
3 months ago |
|
Michael Yang
|
1f766c36fb
ci: use windows-2022 to sign and bundle (#8941)
|
3 months ago |
 Qusai Ismael
|
484a99e428
docs: add LocalLLM app to community integrations (#8953)
|
3 months ago |
 DravenK
|
ec6121c331
docs: ollama zig community lib (#8688)
|
3 months ago |
|
Jeffrey Morgan
|
b86c0a1500
docs: link directly to latest release page for tdm-gcc (#8939)
|
3 months ago |
