HappyZ happyz
happyz synced commits to refs/pull/6811/merge at happyz/llama.cpp from mirror 2024-05-01 10:18:01 -07:00
3ea0d36000 Server: add tests for batch size, different seeds (#6950)
1613ef8d8e CUDA: CUDART < 11.7 workaround for __hmax, __hmax2 (#7019)
c4ec9c0d3d ci : exempt confirmed bugs from being tagged as stale (#7014)
Compare 4 commits »
happyz synced commits to refs/pull/6766/head at happyz/llama.cpp from mirror 2024-05-01 10:18:01 -07:00
58199503a8 Fall back if graph capture fails and address other comments
happyz synced commits to refs/pull/6766/merge at happyz/llama.cpp from mirror 2024-05-01 10:18:01 -07:00
3ea0d36000 Server: add tests for batch size, different seeds (#6950)
1613ef8d8e CUDA: CUDART < 11.7 workaround for __hmax, __hmax2 (#7019)
58199503a8 Fall back if graph capture fails and address other comments
c4ec9c0d3d ci : exempt confirmed bugs from being tagged as stale (#7014)
Compare 5 commits »
happyz synced commits to refs/pull/6810/merge at happyz/llama.cpp from mirror 2024-05-01 10:18:01 -07:00
1613ef8d8e CUDA: CUDART < 11.7 workaround for __hmax, __hmax2 (#7019)
c4ec9c0d3d ci : exempt confirmed bugs from being tagged as stale (#7014)
a8f9b07631 perplexity: more statistics, added documentation (#6936)
Compare 4 commits »
happyz synced commits to refs/pull/6739/merge at happyz/llama.cpp from mirror 2024-05-01 10:18:00 -07:00
1613ef8d8e CUDA: CUDART < 11.7 workaround for __hmax, __hmax2 (#7019)
c4ec9c0d3d ci : exempt confirmed bugs from being tagged as stale (#7014)
a8f9b07631 perplexity: more statistics, added documentation (#6936)
f364eb6fb5 switch to using localizedDescription (#7010)
Compare 10 commits »
happyz synced commits to refs/pull/6511/head at happyz/llama.cpp from mirror 2024-05-01 10:18:00 -07:00
154ad1236e convert-hf-to-gguf-update.py: use triple quoted f-string instead
6d42f3d773 revert changes to convert-hf-to-gguf.py for get_name()
Compare 2 commits »
happyz synced commits to refs/pull/6640/merge at happyz/llama.cpp from mirror 2024-05-01 10:18:00 -07:00
1613ef8d8e CUDA: CUDART < 11.7 workaround for __hmax, __hmax2 (#7019)
c4ec9c0d3d ci : exempt confirmed bugs from being tagged as stale (#7014)
Compare 3 commits »
happyz synced commits to refs/pull/6522/merge at happyz/llama.cpp from mirror 2024-05-01 10:18:00 -07:00
69208a1f8e Merge a37d88568336ec949865e166eaf1454841f4cdb5 into 3ea0d36000
3ea0d36000 Server: add tests for batch size, different seeds (#6950)
1613ef8d8e CUDA: CUDART < 11.7 workaround for __hmax, __hmax2 (#7019)
c4ec9c0d3d ci : exempt confirmed bugs from being tagged as stale (#7014)
a8f9b07631 perplexity: more statistics, added documentation (#6936)
Compare 28 commits »
happyz synced commits to refs/pull/6511/merge at happyz/llama.cpp from mirror 2024-05-01 10:18:00 -07:00
3ea0d36000 Server: add tests for batch size, different seeds (#6950)
154ad1236e convert-hf-to-gguf-update.py: use triple quoted f-string instead
6d42f3d773 revert changes to convert-hf-to-gguf.py for get_name()
1613ef8d8e CUDA: CUDART < 11.7 workaround for __hmax, __hmax2 (#7019)
Compare 6 commits »
happyz synced commits to refs/pull/6412/merge at happyz/llama.cpp from mirror 2024-05-01 10:17:59 -07:00
82ab63cfaa Merge 82aebcf0d989ca3736a5bd53885a857101430828 into 3ea0d36000
82aebcf0d9 Add BF16 code for new ggml_validate_row_data() function
e4949b78a0 Apply ggerganov's fixes for test-backend-ops
3a6baefa1a Fix documentation
f70e923d8e Make the GGML header look nicer
Compare 11 commits »
happyz synced commits to refs/pull/6412/head at happyz/llama.cpp from mirror 2024-05-01 10:17:59 -07:00
82aebcf0d9 Add BF16 code for new ggml_validate_row_data() function
e4949b78a0 Apply ggerganov's fixes for test-backend-ops
3a6baefa1a Fix documentation
f70e923d8e Make the GGML header look nicer
bb6d919c6a Remove bf16 luts
Compare 34 commits »
happyz synced commits to refs/pull/5730/merge at happyz/llama.cpp from mirror 2024-05-01 10:17:59 -07:00
c4ec9c0d3d ci : exempt confirmed bugs from being tagged as stale (#7014)
a8f9b07631 perplexity: more statistics, added documentation (#6936)
f364eb6fb5 switch to using localizedDescription (#7010)
77e15bec62 metal : remove deprecated error code (#7008)
Compare 8 commits »
happyz synced commits to refs/pull/6389/merge at happyz/llama.cpp from mirror 2024-05-01 10:17:59 -07:00
3ea0d36000 Server: add tests for batch size, different seeds (#6950)
1613ef8d8e CUDA: CUDART < 11.7 workaround for __hmax, __hmax2 (#7019)
c4ec9c0d3d ci : exempt confirmed bugs from being tagged as stale (#7014)
Compare 4 commits »
happyz synced commits to refs/pull/6408/merge at happyz/llama.cpp from mirror 2024-05-01 10:17:59 -07:00
25028a21fb Merge dc572071d33b7e029e2d406ade8470e2de91f617 into c4ec9c0d3d
c4ec9c0d3d ci : exempt confirmed bugs from being tagged as stale (#7014)
Compare 2 commits »
happyz synced and deleted reference refs/tags/refs/pull/6950/merge at happyz/llama.cpp from mirror 2024-05-01 10:17:58 -07:00
happyz synced commits to compilade/convert-hf-refactor at happyz/llama.cpp from mirror 2024-05-01 10:17:58 -07:00
dcd8dfa1b5 convert : use a string for the SentencePiece tokenizer path
3870164f47 convert-hf : allow unusual model part names
56f60f5d69 convert-hf : flake8 linter doesn't like semicolons
Compare 3 commits »
happyz synced commits to master at happyz/llama.cpp from mirror 2024-05-01 10:17:58 -07:00
3ea0d36000 Server: add tests for batch size, different seeds (#6950)
1613ef8d8e CUDA: CUDART < 11.7 workaround for __hmax, __hmax2 (#7019)
Compare 2 commits »
happyz synced and deleted reference refs/tags/sl/no-stale-bugs at happyz/llama.cpp from mirror 2024-05-01 10:17:58 -07:00
happyz synced commits to refs/pull/2812/merge at happyz/Fooocus from mirror 2024-05-01 10:17:54 -07:00
d16a54edd6 fix: use LF as line breaks for Docker entrypoint.sh (#2843)
Compare 2 commits »
happyz synced commits to refs/pull/2590/merge at happyz/Fooocus from mirror 2024-05-01 10:17:54 -07:00
d16a54edd6 fix: use LF as line breaks for Docker entrypoint.sh (#2843)
Compare 2 commits »