COMMITS
/ tests/test_llama.py March 23, 2026
A
fix: Qwen 3.5 support (#2152)
Andrei committed
March 22, 2026
A
misc: Add Ruff formatting (#2148)
Andrei committed
July 5, 2025
A
fix: Update reference to in Llama.embed. Closes #2037
Andrei Betlen committed
September 19, 2024
X
fix: Fix memory allocation of ndarray (#1704)
Xu Song committed
A
feat: Update sampling API for llama.cpp (#1742)
Andrei committed
April 30, 2024
A
feat: Update llama.cpp
Andrei Betlen committed
February 26, 2024
A
feat: Update llama.cpp
Andrei Betlen committed
February 21, 2024
December 16, 2023
K
Fix logits_to_logprobs for 2-D and 3-D logits (#1002)
kddubey committed
November 22, 2023
A
tests: add mock_kv_cache placeholder functions
Andrei Betlen committed
A
tests: avoid constantly reallocating logits
Andrei Betlen committed
A
tests: don't mock sampling functions
Andrei Betlen committed
November 21, 2023
A
Use mock_llama for all tests
Andrei Betlen committed
A
tests: Improve llama.cpp mock
Andrei Betlen committed
November 20, 2023
A
Update llama.cpp
Andrei Betlen committed
November 6, 2023
A
Refactor Llama class internals
Andrei Betlen committed
November 3, 2023
A
Migrate inference to llama_batch and llama_decode api (#795)
Andrei committed
November 2, 2023
A
fix: tokenization of special characters: (#850)
Antoine Lizee committed
October 19, 2023
A
Enable finish reason tests
Andrei Betlen committed
A
Re-enable tests completion function
Andrei Betlen committed
September 29, 2023
A
Update llama.cpp
Andrei Betlen committed
September 5, 2023
J
add test to see if llama_cpp.__version__ exists
janvdp committed
August 27, 2023
A
Update llama.cpp
Andrei Betlen committed
A
Update llama.cpp
Andrei Betlen committed
August 25, 2023
A
Strip leading space when de-tokenizing.
Andrei Betlen committed
August 24, 2023
A
Update model path
Andrei Betlen committed
May 19, 2023
A
Fix llama_cpp and Llama type signatures. Closes #221
Andrei Betlen committed
May 2, 2023
A
Refactor server to use factory
Andrei Betlen committed
May 1, 2023
A
Un-skip tests
Andrei Betlen committed
A
Temporarily skip sampling tests.
Andrei Betlen committed
April 29, 2023
L
llama_cpp server: slight refactor to init_llama function
Lucas Doyle committed
L
tests: simple test for server module
Lucas Doyle committed
M
Remove excessive errors="ignore" and add utf8 test
Mug committed
April 26, 2023
M
Also ignore errors on input prompts
Mug committed
April 5, 2023
A
Make Llama instance pickleable. Closes #27
Andrei Betlen committed
A
Add basic tests. Closes #24
Andrei Betlen committed