nicolas
/
hybrid-llama
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
hybrid-llama/turboquant/tools/server/tests/unit
History
Marvin 1dd0700988 hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 
Base: AtomicBot-ai/atomic-llama-cpp-turboquant @ cd5609390. IQK source: ikawrakow/ik_llama.cpp @ fe215a8c (ggml/src/iqk only).

- GGML_IQK_MUL_MAT / GGML_IQK_FLASH_ATTENTION options (default OFF)

- 57 IQK repacked types, blocks, traits; IQK hooks in ggml_compute_forward_mul_mat

- ggml-cpu with IQK ON builds and links; IQK OFF build unaffected

Assisted-by: opencode (Muse Spark)
 		2026-09-05 18:09:49 -03:00
..
test_basic.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_chat_completion.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_compat_anthropic.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_compat_gcp.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_compat_oai_responses.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_completion.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_ctx_shift.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_embedding.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_ignore_eos.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_infill.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_kv_keep_only_active.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_lora.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_mcp_servers.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_proxy.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_rerank.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_router.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_security.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_sleep.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_slot_save.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_speculative.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_stream.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_template.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_tokenize.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_tool_call.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_tools_builtin.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00
test_vision_api.py hybrid-llama: merge ik_llama IQK CPU GEMM into TurboQuant fork 2026-09-05 18:09:49 -03:00