City 558a764713 Force FP32 compute in GLM4 FFN Down (#13101) ...

* Force FP32 compute in cuBLAS GEMM

* Revert "Force FP32 compute in cuBLAS GEMM"

This reverts commit 6efd872732159ab88ee7b3c1d77ba5ebc83079bd.

* Force F32 compute in GLM4 ffn down

* Edit comment to clarify issue

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

2025-04-25 14:38:34 +02:00

..

CMakeLists.txt

cmake : do not include ./src as public for libllama (#13062)

2025-04-24 16:00:10 +03:00

llama-adapter.cpp

llama : make loras compatible with repacking (#12593)

2025-03-27 08:24:10 +02:00

llama-adapter.h

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

llama-arch.cpp

llama : DeepSeek V2/V3 MLA implementation (#12801)

2025-04-15 09:49:57 +03:00

llama-arch.h

llama : DeepSeek V2/V3 MLA implementation (#12801)

2025-04-15 09:49:57 +03:00

llama-batch.cpp

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-batch.h

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

llama-chat.cpp

mtmd : support SmolVLM (version 1 and 2) (#13050)

2025-04-22 16:24:54 +02:00

llama-chat.h

mtmd : support SmolVLM (version 1 and 2) (#13050)

2025-04-22 16:24:54 +02:00

llama-context.cpp

graph : make FA compatible with MLA + add initial Metal kernels (#12953)

2025-04-17 18:16:36 +03:00

llama-context.h

Load all MoE experts during warmup (#11571)

2025-03-14 13:47:05 +01:00

llama-cparams.cpp

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-cparams.h

Load all MoE experts during warmup (#11571)

2025-03-14 13:47:05 +01:00

llama-grammar.cpp

tool-call: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)

2025-03-05 13:05:13 +00:00

llama-grammar.h

tool-call: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)

2025-03-05 13:05:13 +00:00

llama-graph.cpp

Force FP32 compute in GLM4 FFN Down (#13101)

2025-04-25 14:38:34 +02:00

llama-graph.h

llama : DeepSeek V2/V3 MLA implementation (#12801)

2025-04-15 09:49:57 +03:00

llama-hparams.cpp

hparams : add SWA rope parameters (#12374)

2025-03-14 09:03:24 +02:00

llama-hparams.h

llama : DeepSeek V2/V3 MLA implementation (#12801)

2025-04-15 09:49:57 +03:00

llama-impl.cpp

GGUF: C++ refactor, backend support, misc fixes (#11030)

2025-01-07 18:01:58 +01:00

llama-impl.h

cleanup: fix compile warnings associated with gnu_printf (#11811)

2025-02-12 10:06:53 -04:00

llama-io.cpp

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

llama-io.h

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

llama-kv-cache.cpp

llama : DeepSeek V2/V3 MLA implementation (#12801)

2025-04-15 09:49:57 +03:00

llama-kv-cache.h

kv-cache : simplify + fix warning for recurrent models (#12756)

2025-04-04 21:48:10 +03:00

llama-memory.cpp

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

llama-memory.h

kv-cache : simplify + fix warning for recurrent models (#12756)

2025-04-04 21:48:10 +03:00

llama-mmap.cpp

mmap : skip resource limit checks on AIX (#12541)

2025-03-24 12:17:10 +02:00

llama-mmap.h

llama-mmap: fix missing include (#11796)

2025-02-10 20:58:18 +02:00

llama-model-loader.cpp

model : print tensor size during load (#12711)

2025-04-02 16:38:54 +03:00

llama-model-loader.h

llama : add option to override model tensor buffers (#11397)

2025-04-02 14:52:01 +02:00

llama-model.cpp

graph : make FA compatible with MLA + add initial Metal kernels (#12953)

2025-04-17 18:16:36 +03:00

llama-model.h

llama : DeepSeek V2/V3 MLA implementation (#12801)

2025-04-15 09:49:57 +03:00

llama-quant.cpp

quantize: Handle user-defined quantization levels for additional tensors (#12511)

2025-04-13 21:29:28 +03:00

llama-quant.h

llama : refactor src/llama.cpp (#10902)

2025-01-03 10:18:53 +02:00

llama-sampling.cpp

llama: fix error on bad grammar (#12628)

2025-03-28 18:08:52 +01:00

llama-sampling.h

llama : add llama_vocab, functions -> methods, naming (#11110)

2025-01-12 11:32:42 +02:00

llama-vocab.cpp

mtmd : Support Pixtral 12B (#13065)

2025-04-23 20:21:59 +02:00

llama-vocab.h

llama : remove notion of CLS token (#11064)

2025-01-12 12:15:53 +02:00

llama.cpp

llama : add option to override model tensor buffers (#11397)

2025-04-02 14:52:01 +02:00

unicode-data.cpp

server : better security control for public deployments (#9776)

2024-10-08 13:27:04 +02:00

unicode-data.h

llama : reduce compile time and binary size (#9712)

2024-10-02 15:49:55 +02:00

unicode.cpp

repo : update links to new url (#11886)

2025-02-15 16:40:57 +02:00

unicode.h

unicode : improve naming style (#10838)

2024-12-16 12:31:45 +02:00